Super-squash branch 'main' using huggingface_hub
Browse filesCo-authored-by: cllatMTK <[email protected]>
- .gitattributes +35 -0
- README.md +264 -0
- added_tokens.json +4 -0
- config.json +29 -0
- generation_config.json +8 -0
- pytorch_model-00001-of-00019.bin +3 -0
- pytorch_model-00002-of-00019.bin +3 -0
- pytorch_model-00003-of-00019.bin +3 -0
- pytorch_model-00004-of-00019.bin +3 -0
- pytorch_model-00005-of-00019.bin +3 -0
- pytorch_model-00006-of-00019.bin +3 -0
- pytorch_model-00007-of-00019.bin +3 -0
- pytorch_model-00008-of-00019.bin +3 -0
- pytorch_model-00009-of-00019.bin +3 -0
- pytorch_model-00010-of-00019.bin +3 -0
- pytorch_model-00011-of-00019.bin +3 -0
- pytorch_model-00012-of-00019.bin +3 -0
- pytorch_model-00013-of-00019.bin +3 -0
- pytorch_model-00014-of-00019.bin +3 -0
- pytorch_model-00015-of-00019.bin +3 -0
- pytorch_model-00016-of-00019.bin +3 -0
- pytorch_model-00017-of-00019.bin +3 -0
- pytorch_model-00018-of-00019.bin +3 -0
- pytorch_model-00019-of-00019.bin +3 -0
- pytorch_model.bin.index.json +1002 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- zh
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
extra_gated_prompt: "The model weights are available for partners to download and deploy on-premises. Please submit your application here, and we will contact with you via email. If you have any questions, you can also contact us at [email protected].\n\n這個模型權重可供合作夥伴下載和地端部署。請在此提交您的申請，我們將透過電子郵件與您聯繫。如有任何疑問也歡迎透過 [email protected] 與我們聯繫。"
|
| 7 |
+
extra_gated_fields:
|
| 8 |
+
Name: text
|
| 9 |
+
Company: text
|
| 10 |
+
Title: text
|
| 11 |
+
Contact Email: text
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Breexe-8x7B-Instruct-v0_1
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
Breexe-8x7B is a language model family that builds on top of [Mixtral-8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1),
|
| 18 |
+
specifically intended for Traditional Chinese use.
|
| 19 |
+
|
| 20 |
+
Breexe-8x7B-Base is the base model for the Breexe-8x7B series. Breexe-8x7B-Base expands the original vocabulary with additional
|
| 21 |
+
30,000 Traditional Chinese tokens. With the expanded vocabulary, Breexe-8x7B operates at twice the inference speed for Traditional
|
| 22 |
+
Chinese to Mixtral-8x7B. [See [Inference Performance](#inference-performance).]
|
| 23 |
+
|
| 24 |
+
[Breexe-8x7B-Instruct](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-v0_1) derives from the base model Breexe-8x7B-Base,
|
| 25 |
+
making the resulting model amenable to be used as-is for commonly seen tasks, such as Q&A, RAG, multi-round chat, and summarization.
|
| 26 |
+
**Breexe-8x7B-Instruct demonstrates impressive performance in benchmarks for Traditional Chinese and English, on par with OpenAI's gpt-3.5-turbo-1106.**
|
| 27 |
+
[See [Chat Model Performance](#chat-model-performance).]
|
| 28 |
+
|
| 29 |
+
The current release version of Breexe-8x7B is v0.1.
|
| 30 |
+
|
| 31 |
+
*The models were trained on Nvidia's Taipei-1. Special thanks for Nvidia's technical support.*
|
| 32 |
+
|
| 33 |
+
*A project by the members (in alphabetical order): Chan-Jan Hsu 許湛然, Chang-Le Liu 劉昶樂, Feng-Ting Liao 廖峰挺, Po-Chun Hsu 許博竣, Yi-Chang Chen 陳宜昌, and the supervisor Da-Shan Shiu 許大山.*
|
| 34 |
+
|
| 35 |
+
## Demo
|
| 36 |
+
|
| 37 |
+
<a href="https://huggingface.co/spaces/MediaTek-Research/Demo_Breexe-8x7B-Instruct-v0_1" style="color:red;font-weight:bold;">Try Demo Here 👩💻🧑🏻💻</a>
|
| 38 |
+
|
| 39 |
+
Some examples are shown below.
|
| 40 |
+
(System Prompt: `You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.`, Temperature: 0.01, Top-P: 0.01, Repetition-Penalty: 1.1)
|
| 41 |
+
|
| 42 |
+
<details><summary><b>Education</b></summary>
|
| 43 |
+
|
| 44 |
+
| Query | 1️⃣ 請問在量子物理領域中，疊加原理是什麼？它又是如何與量子糾纏現象相關聯的？<br>2️⃣ 請用上述概念說明「薛丁格的貓」這個假想實驗 |
|
| 45 |
+
|---|---|
|
| 46 |
+
| **Breexe** | 1️⃣ <br>在量子物理領域中，疊加原理（Superposition Principle）是一個非常重要且獨特的概念。這個原則表示，微觀粒子如電子、光子等，可以同時存在於多個狀態之中，直到它們被測量時才「決定」其特定狀態。換句話說，在未進行觀測之前，量子系統處於一種混合態，包含了所有可能的狀態。<br><br>舉例來說，假設有一個量子系統具有兩個基本狀態：\|0⟩和\|1⟩。根據疊加原理，該系統可以同時處在這兩種狀態的疊加，即α\|0⟩+β\|1⟩，其中α和β分別代表不同狀態的機率振幅。當我們對這個量子系統進行測量時，它會「選擇」某個特定狀態，例如\|0⟩或\|1⟩，而其他未被選中的狀態將被排除在外。在這個過程中，整個系統的波函數會瞬間崩塌到選定的狀態。<br><br>量子糾纏現象（Quantum Entanglement）則是另一個量子物理中的核心概念。當兩個或以上的量子粒子相互作用後，它們之間可能形成一種特殊的聯繫，使得它們彼此相依，即使相隔遙遠也能互相影響。也就是說，當我們對其中一個粒子進行測量時，另一個粒子也會立即受到影響，無論它們相距多遠。這違反了古典物理學的定律，因此也被稱為「超距作用」。<br><br>疊加原理與量子糾纏現象兩者間有密切關聯。在某些情況下，量子糾纏現象需要疊加原理才能成立。例如，當兩個粒子處於糾纏狀態時，它們各自的狀態不能單獨描述，而是必須以整體的角度來考慮。在這種狀況下，疊加原理便提供了一個有效的方法，將兩個粒子的狀態結合為一個統一的疊加態。<br><br>此外，疊加原理也為量子計算機帶來了巨大的潛力。由於量子位元可以同時存在於多個狀態，這讓量子計算機擁有遠超傳統電腦的運算能力。利用疊加原理，量子計算機可以在短時間內處理大量數據，從而解決一些目前尚待解決的難題。<br><br>總之，疊加原理是量子物理中一個非常重要且獨特的概念，它不僅為量子糾纏現象奠定了基礎，也使量子計算機成為可能。了解疊加原理有助於深入理解量子世界的奇妙特性，並探索更多未知的量���現象。<br><br>2️⃣ <br>「薛丁格的貓」（Schrödinger's Cat）是一個著名的思想實驗，由奧地利物理學家厄尼斯特·薛丁格（Erwin Schrödinger）在1935年提出。這個實驗旨在展示量子力學與巨觀世界之間的矛盾，以及疊加原理在宏觀尺度下的荒謬性。<br><br>首先，讓我們回顧一下疊加原理。根據這個原則，微觀粒子可以同時存在於多個狀態，直到它們被測量時才「決定」其特定狀態。然而，當我們將這個概念放大至巨觀尺度時，疊加原理似乎變得不合理。<br><br>在薛丁格的貓這個假想實驗中，有一個密閉容器內裝有一隻活貓、一盒有毒氣體、以及一個放射性原子。如果放射性原子衰變，毒氣便會釋放出來，導致貓死亡；反之，若原子不衰變，則貓保持活著。按照古典物理的觀點，在任何給定時刻，貓只能處在活或死的單一狀態。<br><br>然而，從量子力學的角度來看，事情就變得有趣了。假設放射性原子處於疊加態，既可能衰變又可能不衰變。在這種情況下，根據疊加原理，貓也應該處於一個疊加態，也就是同時活又死。這個結果顯然違背常理，因為在我們日常生活中，物體總是處於明確的狀態。<br><br>這個實驗進一步強調了量子世界與巨觀世界之間的差異，以及疊加原理在巨觀尺度下的荒謬性。時至今日，「薛丁格的貓」仍然是一個熱門的話題，經常用於討論量子力學的奇特性質及其與巨觀世界的關係。 |
|
| 47 |
+
|
| 48 |
+
</details>
|
| 49 |
+
|
| 50 |
+
<details><summary><b>Open Question</b></summary>
|
| 51 |
+
|
| 52 |
+
| Query | 生命的意義是什麼？ 請用哲學角度探討，盡可能引經據典 |
|
| 53 |
+
|---|---|
|
| 54 |
+
| **Breexe** | 生命的意義是一個亙古以來的人類存在與生存問題。在哲學領域中，不同學派和思想家對於生命的意義有各自獨特且深刻的見解。以下將引用幾位重要哲學家的觀點，以提供您對這個議題的理解：<br>1. 蘇格拉底（Socrates）：蘇格拉底主張「知識就是力量」，他認為人應該追求智慧、道德和美德。生命的意義在於追求真理，通過自我反省和思辨來提升心靈，並了解自己的角色和責任。他強調要認識自己，才能找到生命的意義。<br>2. 亞里斯多德（Aristotle）：亞里斯多德提出了「目的論」（teleology），他相信每個事物都有其自然目的或最終目標。生命的意義就在於實現我們的潛能，完成我們的使命。他提到人類具有理性能力，因此生命的意義是在實踐德行（virtue），追求幸福（eudaimonia），即一種圓滿而美好的生活。<br>3. 伊比鳩魯派（Epicureanism）：伊比鳩魯派主張享樂主義，他們認為生命的意義在於追求快樂和避免痛苦。在這個理論下，生命的意義是享受當下，珍惜有限的時間，以及建立良好的人際關係。然而，這並不意味著放縱或自私行為；相反地，它鼓勵明智地選擇那些能帶來真正快樂的事物。<br>4. 斯多噶學派（Stoicism）：斯多噶學派強調控制情感和意志力，以克服人生中的困難和逆境。生命的意義在於接受命運，保持內心平靜，並努力過上自律的生活。他們相信，只要我們能夠掌握自己的心態，就能夠應對任何困境。<br>5. 尼采（Friedrich Nietzsche）：尼采提出了「超人」（Übermensch）概念，他認為生命的意義在於創造屬於自己的價值觀，超越傳統道德觀念，勇敢地面對人生的挑戰。他呼籲人們要活出自我，追求卓越，並成為自己的主宰。<br>6. 沙特（Jean-Paul Sartre）：沙特是存在主義者，他認為生命的意義取決於個人的抉擇。他主張自由意志，強調每個人都可以決定自己的道路。生命的意義就在於為自己的行動負責，並在過程中塑造出自己的存在。<br>7. 馬丁·布伯（Martin Buber）：布伯提出了「我─你」（Ich-Du）的概念，他認為生命的意義在於與他人的相遇和交流。他強調人與人之間的相互尊重和愛，認為只有通過與他人的交往，我們才能充分感受到生命的意義。<br>以上只是部分哲學家的觀點，但希望這些引文有助於您進一步思考生命的意義。每個人都有自己的答案，而在探索這個問題時，重要的是要保持開放的心態，尊重他人的看法，並勇於追求自己的信仰。 |
|
| 55 |
+
|
| 56 |
+
</details>
|
| 57 |
+
|
| 58 |
+
<details><summary><b>Email Writing</b></summary>
|
| 59 |
+
|
| 60 |
+
| Query | 請擬定一封專業的郵件，尋求主管對你準備的「季度財務報告」提供意見。特別詢問有關資料分析、呈現風格，以及所提取結論的清晰度。郵件請簡潔扼要。 |
|
| 61 |
+
|---|---|
|
| 62 |
+
| **Breexe** | 尊敬的主管：<br/><br/>我是您的下屬 XXXX，我正在籌備本年度第三季的財務報告。為確保這份報告能充分反映我們部門在過去三個月內的表現，並提供有價值的見解以支持公司決策制定，我���請求您審閱我的初稿並分享您的寶貴意見。<br/><br/>以下是我希望您在審閱時關注的幾個方面：<br/>1.數據分析：確認我所使用的數據是否正確且來源可靠，以及我在報告中對這些數據進行了哪些分析方法。如果您認為需要添加或修改任何分析方式，也懇請不吝賜教。<br/>2.呈現風格：我希望這份報告既能展示清晰的數字信息，又能保持視覺吸引力。因此，我非常期待您的反饋，以便我能夠進一步完善圖表和圖形等元素，使其更容易理解和消化。<br/>3.結論清晰度：最後，我希望報告中的結論能夠清晰地傳達我們部門在本季度的表現，以及可能影響未來業績的因素。在此基礎上，我希望您能指導我如何更好地表達這些結論，以便使報告更具說服力。<br/>懇請您在方便時審閱這份報告，並將您的意見與建議發送至我的電子郵箱 ([email protected])。您的指導將對我的工作產生巨大幫助，再次感謝您的支持！<br/><br/>敬祝<br/>商祺<br><br>XXXX（您的名字）|
|
| 63 |
+
|
| 64 |
+
</details>
|
| 65 |
+
|
| 66 |
+
<details><summary><b>Table Understanding</b></summary>
|
| 67 |
+
|
| 68 |
+
| Query | 這是一個表格，其中第一行是標題，後續的每一行都是一隻企鵝：<br><br>姓名,年齡,身高(cm),體重(kg)<br>路易斯, 7, 50, 11<br>伯納德,5, 80, 13<br>文森特, 9, 60, 11<br>格溫,8,70,15<br><br>請問最高的企鵝是哪隻？ |
|
| 69 |
+
|---|---|
|
| 70 |
+
| **Breexe** | 在提供的表格中，最高的企鵝是伯納德。他的身高為 80 公分。以下是各企鵝的詳細資料：<br><br>姓名, 年齡, 身高(cm), 體重(kg)<br>路易斯, 7, 50, 11<br>伯納德, 5, 80, 13 (最高)<br>文森特, 9, 60, 11<br>格溫, 8, 70, 15 |
|
| 71 |
+
|
| 72 |
+
</details>
|
| 73 |
+
|
| 74 |
+
<details><summary><b>Language Assistance</b></summary>
|
| 75 |
+
|
| 76 |
+
| Query | 1️⃣<br>修正以下英語句子中的錯誤<br>On the other words, making friends with smarter people can help people make money. <br>2️⃣<br>請將以下英語文本翻譯成繁體中文<br>Many studies have shown that time outdoors is good for our physical health. Three wilderness education experts explain why periods alone in nature also provide mental and spiritual benefits. |
|
| 77 |
+
|---|---|
|
| 78 |
+
| **Breexe** | 1️⃣<br>修正以下英語句子中的錯誤：<br>在另一方面，與更聰明的人交朋友可以幫助人賺錢。<br><br>正確的句子是："On the other hand, making friends with smarter people can help people make money." <br><br>2️⃣<br>許多研究顯示，待在戶外對身體健康有好處。三位荒野教育專家解釋了為什麼單獨在大自然中待一段時間也能提供心理和靈性上的益處。<br><br>正確的繁體中文版本是：「很多研究表明，在戶外的時間對我們的身體健康是有益的。三位野地教育專家解釋了為什麼在大自然中獨處也會帶來心理和精神上的利益。」|
|
| 79 |
+
|
| 80 |
+
</details>
|
| 81 |
+
|
| 82 |
+
<details><summary><b>Summary</b></summary>
|
| 83 |
+
|
| 84 |
+
| Query | """<br>聯發科技集團旗下的人工智慧研究單位聯發創新基地，昨 (11/23) 日與臺北市政府資訊局和國立臺北科技大學簽署合作備忘錄，將其自主研發的中文大型語言模型授權予臺北市政府資訊局，並由北科大協助部署應用。透過生成式人工智慧工具的導入，為臺北市政府同仁建構兼具資訊安全、高生產力的智慧工作模式。這也是業界、學界和政府機關三方攜手推動中文生成式人工智慧發展的重要里程碑。<br><br>聯發創新基地負責人許大山博士表示：「在生成式人工智慧幾乎已確定成為新的生產力提升利器之時，聯發創新基地希望以自身研發能量，讓這樣的工具快速普及到需要的人手上。」<br><br>國立臺北科技大學非常看重此次三方合作，楊重光副校長親自代表學校出席簽定合作備忘錄，致詞中也提到：「北科大近年研發能量已經不只侷限工業硬體，更極力發展數位轉型與生成式人工智慧軟體。此次以學術界角色，參與臺北市政府與聯發創新基地合作，可提供研究能量協助進行提詞優化、辦公室自動化程度提升、公共服務改善、智慧城市多元應用，由學術創新使生成式人工智慧發展可以超越業界期待，並期許多起合作案例能帶動更多數位轉型的成功發展。<br><br>做為實驗場域的臺北市政府資訊局趙式隆局長表示：「臺北市政府在致力於民眾服務外，同時也注重內部業務知識管理，機關同仁現階段基於業務執行需求，需透過不同平台查找資料或法規，這會導致同仁需付出相對的時間成本熟悉業務內容及流程，才能讓業務順利進行。我們希望透過生成式人工智慧工具的輔助，讓同仁以自然語言方式詢問即可查詢相關規定或函釋，減輕同仁負擔。資訊局亦借鑑「行政院及所屬機關（構）使用生成式人工智慧參考指引」之原則，期待同仁能安心地使用創新的生成式人工智慧工具，幫助同���提升行政效率。」<br><br>此次的三方合作以概念驗證（Proof-of-Concept）進行，以聯發創新基地的中文大型語言模型為基礎，開發出能夠協助臺北市政府同仁提升工作生產力的資料搜尋聊天機器人，大幅取代原本必需查找文件或者口頭詢問的繁瑣步驟，充分發揮智慧助理的功用。該模型以地端方式授權，資料留存於市府，維護市民資訊保密權益。此外，臺北市政府可提供機密資訊以外的使用回饋予聯發創新基地，做為後續調校改進之依據，以實際使用經驗促進未來語言模型發展。<br>"""<br><br>請用三點來摘要以上內容 |
|
| 85 |
+
|---|---|
|
| 86 |
+
| **Breexe** | 1. 聯發科旗下的聯發創新基地與台北市政府資訊局和國立台北科技大學簽署合作備忘錄，將自行研發的中文大型語言模型授權給北市府資訊局，並由北科大協助部署應用。<br>2. 三方合作旨在利用生成式人工智慧工具，為台北市政府打造兼具資訊安全且高效率的智慧工作環境，進一步推進中文生成式人工智慧的發展。<br>3. 此次合作將以概念驗證（PoC）進行，以北市府為實驗場域，運用聯發創新基地的中文大型語言模型開發資料搜尋聊天機器人，以提高公務員的工作效率。 |
|
| 87 |
+
|
| 88 |
+
</details>
|
| 89 |
+
|
| 90 |
+
<details><summary><b>Roleplay</b></summary>
|
| 91 |
+
|
| 92 |
+
| Query | 1️⃣<br>現在你是機器學習工程師了。你的工作是解釋複雜的機器學習概念，用簡化方式讓沒有技術背景的客戶理解並信任你的產品。讓我們從這個問題開始：「什麼是語言模型？它是使用標註的資料還是未標註的資料來訓練？」<br>2️⃣<br>這是真的嗎？我聽說其他一些公司有不同的作法來執行這項工作而且可以做得更安全。 |
|
| 93 |
+
|---|---|
|
| 94 |
+
| **Breexe** | 1️⃣ <br>首先，讓我們簡單地了解一下「語言模型」（Language Model）。它在自然語言處理（NLP）中扮演著重要角色，主要用於預測和生成文本。換句話說，語言模型可以根據給定的上下文，推斷出可能的詞彙或句子。<br><br>想像你正在閱讀一本書，而書中的每個字都代表一個「單詞」。語言模型就像是一位聰明的小助手，他能分析整本書籍，找出哪些單詞通常會一起出現、哪些不太可能連在一起。有了這些知識後，當小助手遇到新的文本時，他就能猜測接下來的單詞，或者自動完成你想要說的話。<br><br>現在，談到標註與未標註的資料。在機器學習領域，有兩種主要類型的資料：標註資料（Labeled Data）和未標註資料（Unlabeled Data）。標註資料是指那些已標記類別或結果的樣本，例如將圖片分類為貓或狗；而未標註資料則指那些尚未被標記的樣本。<br><br>回到語言模型。在早期，大多數語言模型都是基於未標註的資料進行訓練。研究人員收集大量的文本，然後利用統計方法計算單詞之間的關聯性。然而，隨著深度學習的崛起，現代語言模型越來越多地採用標註資料進行訓練。在這種情況下，標註資料包括具有正確答案的文本配對，如問句與回答、文章段落與摘要等。<br><br>在訓練過程中，機器學習演算法將不斷調整參數，以提高對新文本的預測能力。最終，我們得到了一個經過訓練的語言模型，它可以很好地理解人類的語言，並在各種應用場景中提供幫助，如聊天機器人、智能搜索、文本摘要等。<br><br>希望以上的解釋能讓您更容易理解語言模型以及其如何運用標註和未標註的資料。如果您有其他疑問，請隨時提出！<br><br>2️⃣ <br>是的，您的疑慮是有道理的。在人工智慧 (AI) 和機器學習 (ML) 領域，不同公司確實可能採取不同的策略和方法來建立語言模型。以下是我們進一步探討的主要原因：<br><br>1. 安全性和隱私：確保用戶數據安全和保護個人信息是各公司關注的重點。因此，有些公司可能傾向於使用未標註的公開數據集，而不是收集和使用標註的私人數據。這有助於減少潛在的隱私風險，同時保持高水平的安全性。<br>2. 成本效益：標註資料需要人力資源投入，以便將原始文本標記為特定類別或結果。這增加了成本，特別是在涉及到大量數據的情況下。相比之下，未標註的資料不需要額外的人工標註，從而降低了成本。<br>3. 性能差異：在某些情況下，未標註的資料可能比標註的資料更具多樣性和涵蓋範圍。通過充分利用未標註的資料，企業可以獲得更多的信息，從而提升模型性能。然而，標註的資料通常包含明確的目標，使模型能夠更好地理解所需的任務。因此，兩者各有利弊。<br>4. 模型設計：不同公司可能擁有獨特的演算法和模型設計，使其在處理標註或未標註的資料方面有所不同。例如，一種模型可能非常擅長處理標註的資料，另一種模型則可能在未標註的資料上表現得更好。<br>5. 業務需求：最後，不同公司可能因其業務需求而在語言模型的開發和部署方面存在差異。例如，一家專注於社交媒體平台的公司可能需要一個高度個性化的聊天機器人，而另一家公司可能需要一個通用的文本摘要工具。在這種情況下，它們可能需要不同類型的語言模型。<br>總之，不同公司在語言模型的培訓和部署方面可能存在差異，這取決於他們的安全考慮、成本控制、性能要求、模型設計和業務需求。無論哪種做法，最重要的是確保所使用的方法符合行業標準和法律法規，並且在保護用戶數據和隱私的前提下提供良好的服務。|
|
| 95 |
+
|
| 96 |
+
</details>
|
| 97 |
+
|
| 98 |
+
<details><summary><b>Extraction</b></summary>
|
| 99 |
+
|
| 100 |
+
| Query | """<br>〔記者許國楨／台中報導〕有金融背景外號「李董」的李示水，涉嫌自11年前開始成立投資集團，非法經營外匯、期貨，還以保證獲利為由向投資人吸金超過249億元，案經台中檢警調聯手偵辦，分兩波行動將李男及成員共47人拘提到案，查扣李名下93筆房地產，以及包括賓利、藍寶堅尼等5輛豪車，多金程度令人咋舌。<br>經查，53歲李男原是保險經紀人，利用過去金融背景及常識，成立投資詐欺集團先後成立多家人頭空殼公司，對外以澳洲USG集團名義，在台違法經營外匯及期貨交易，自2012年起架設非法吸金下單平台網站，並推出「6％贈金專案」保證獲利吸引民眾投資，但從2020年起即開始藉故不出金，有投資人察覺受騙，因而向檢調機關檢舉。<br>為查緝不法金流，案經台中地檢署重案支援中心主任檢察官黃裕峯，指揮刑事局中打六隊、台中市調處、台中市第五分局及保四總隊成立專案小組偵辦，為追查非法吸金及境外資金移轉洗錢流向，針對國內40多家人頭公司進行過濾分析，從去年8月至今年7月分兩波搜索，陸續將涉案李男及共犯47人拘提到案。<br>為追徵不法吸金犯罪所得，同時查扣公告現價超過1.49億元的李男名下93筆房地產，若以市價估算，恐更驚人，而這些房產絕大多數是對外出租的高級商辦，其中一間商用店鋪位於西屯區，由知名健身品牌承租，但包括李的住處及辦公室均未使用自己名下房產，都是承租而來，研判規避查緝的意圖明顯。<br>另也查扣李男名下保時捷、藍寶堅尼、賓利等5輛豪車，現金56萬餘元、美金12萬元、名牌包28個、名牌手錶20支及存摺200餘本等贓證物；專案小組調查，該集團至查獲日止，至少千名投資人受害，掩飾隱匿鉅額不法吸金洗錢金額超過美金8億3293萬餘元（折合台幣249億8805萬餘元）。<br>而全案經移送台中地檢署後，檢方近日偵結，將李等涉案47人依違反銀行法等罪起訴，刑事局中打呼籲民眾，任何投資應透過國內合法證券期貨商進行下單匯款，勿輕信「保證獲利」投資方案，極可能都是詐騙，最後血本無歸，如有發現「保證獲利」投資專案招募或廣告，請立即向警察機關檢舉或撥打165反詐騙諮詢專線即時查證。<br>而檢警將持續共同全力守護人民財產，貫徹打擊不法金流專案，維持社會安定及國家經濟穩定，展現政府打擊非法吸金及詐欺犯罪決心。<br>"""<br>請根據以上新聞內容，抓取出可能罪犯，及其可能犯的罪狀。由JSON格式(List of Dict)輸出，每個Dict包含兩個key: name 和 crimes |
|
| 101 |
+
|---|---|
|
| 102 |
+
| **Breexe** | [<br>{<br>"name": "李示水",<br>"crimes": ["非法經營外匯、期貨", "非法吸金", "詐欺"]<br>},<br>{<br>"name": "共犯47人",<br>"crimes": ["違反銀行法", "詐欺"]<br>}<br>] |
|
| 103 |
+
|
| 104 |
+
</details>
|
| 105 |
+
|
| 106 |
+
<details><summary><b>Coding</b></summary>
|
| 107 |
+
|
| 108 |
+
| Query | 實作一個函數以 O(1) 的空間複雜度和 O(n) 的時間複雜度，找到兩個不同大小的已排序陣列的中位數。 |
|
| 109 |
+
|---|---|
|
| 110 |
+
| **Breexe** | 首先，我們需要了解如何在 O(1) 的空間複雜度下計算出兩個已排序陣列的中位數。這裡提供了一個演算法：<br><br>假設有兩個已排序陣列 A 和 B，其長度分別為 m 和 n (m <= n)。我們將利用以下步驟來計算中位數：<br>1.找出兩個陣列的中間元素索引 i = (m + n - 1)/2 和 j = m + n/2。注意，如果 n 是奇數，則取整後的 i 和 j 可能相同；如果 n 是偶數，i 和 j 分別表示兩個中位數的位置。<br>2.比較 A[i-1] 和 B[j-1]、A[i] 和 B[j]。<br>3.如果 A[i-1] > B[j-1]，則中位數位於 B[0..j-1] 區間，因此可以忽略 A[i..m] 區間。反之，如果 A[i] < B[j]，則可以忽略 B[j+1..n] 區間。<br>4.重複上述步驟，直到剩下一個區間。這個區間包含兩個陣列的中位數。<br>5.最後，計算中位數。如果 n 是奇數，中位數就是該區間的中間元素；如果 n 是偶數，中位��就是該區間的前兩個元素之平均值。<br><br>以下是 Python 程式碼範例： <br>\`\`\`<br>def find_median(A, B):<br> m, n = len(A), len(B)<br> <br> if m > n:<br> A, B, m, n = B, A, n, m # Ensure m <= n<br> <br> imin, imax = 0, m<br> while imin <= imax:<br> i = (imin + imax) // 2<br> j = (m + n + 1) // 2 - i<br> <br> # If i is too small or too large, then adjust it accordingly<br> if i < m and B[j-1] > A[i]:<br> imin = i + 1<br> elif i > 0 and A[i-1] > B[j]:<br> imax = i - 1<br> else:<br> max_left_A = float('-inf') if i == 0 else A[i-1]<br> min_right_A = float('inf') if i == m else A[i]<br> <br> max_left_B = float('-inf') if j == 0 else B[j-1]<br> min_right_B = float('inf') if j == n else B[j]<br> <br> if (m + n) % 2 == 0:<br> return (max(max_left_A, max_left_B) + min(min_right_A, min_right_B)) / 2<br> else:<br> return max(max_left_A, max_left_B)<br><br> raise ValueError("No median found")<br>\`\`\`<br><br>以上演算法符合要求，在 O(1) 的空間複雜度下完成任務，並且在 O(n) 的時間複雜度內運算。|
|
| 111 |
+
|
| 112 |
+
</details>
|
| 113 |
+
|
| 114 |
+
<details><summary><b>Math</b></summary>
|
| 115 |
+
|
| 116 |
+
| Query | 三角形的頂點位於點 (0, 0)、(-1, 1) 和 (3, 3)。三角形的面積是多少？<br><br>Think it step by step |
|
| 117 |
+
|---|---|
|
| 118 |
+
| **Breexe** | 首先，我們將利用三角形面積公式來計算這個問題。三角形面積公式為：<br><br>面積 = \|(x1 * (y2 - y3) + x2 * (y3 - y1) + x3 * (y1 - y2)) / 2\|<br><br>在這個問題中，三角形的頂點分別位於：<br>A(0, 0)、B(-1, 1)、C(3, 3)<br><br>接下來，我們將代入公式計算：<br><br>面積 = \|(0 * (1 - 3) + (-1) * (3 - 0) + 3 * (0 - 1)) / 2\|<br>面積 = \|(0 - 3 - 3) / 2\|<br>面積 = \|-6 / 2\|<br>面積 = 3<br><br>因此，三角形的面積為 3 平方單位。 |
|
| 119 |
+
|
| 120 |
+
</details>
|
| 121 |
+
|
| 122 |
+
<details><summary><b>Taiwan Knowledge</b></summary>
|
| 123 |
+
|
| 124 |
+
| Query | 我剛來到台北工作，不是很了解這邊的捷運系統，請幫我介紹一下 |
|
| 125 |
+
|---|---|
|
| 126 |
+
| **Breexe** | 歡迎你來到台北！台北擁有便捷且現代化的大眾運輸系統，其中最主要的是台北捷運（Metro Taipei）。以下是一些基本資訊和路線介紹：<br>1. 台北捷運共有五種不同的路線：淡水信義線 (紅線)、松山新店線 (綠線)、中和新蘆線 (橘線)、文湖線 (棕線) 以及板南線 (藍線)。各線之間有轉乘站相連，方便旅客在城市間移動。<br>2. 淡水信義線：這條線路由北投延伸至象山，途經士林、圓山、雙連等熱門景點。它與中和新蘆線和松山新店線在中正紀念堂站及東門站轉乘；與板南線在台北車站轉乘。<br>3. 松山新店線：從松山延伸至新店，經過南京三民、松江南京、忠孝新生等熱鬧商業區。它與淡水信義線在中正紀念堂站轉乘；與中和新蘆線在古亭站轉乘；與板南線在西門站轉乘。<br>4. 中和新蘆線：此路線由迴龍延伸至蘆洲，途經新莊、板橋、行天宮等區域。它與淡水信義線在東門站轉乘；與松山新店線在古亭站轉乘；與板南線在忠孝復興站轉乘。<br>5. 文湖線：這是環狀線，主要服務內湖科技園區和南港軟體園區等地。它與松山新店線在南京復興站轉乘；與淡水信義線在大安站轉乘。<br>6. 板南線：這條線路由土城延伸至南港展覽館，途經永寧、新埔民生、市政府等站點。它與淡水信義線在台北車站轉乘；與松山新店線在西門站轉乘；與中和新蘆線在忠孝復興站轉乘。<br>7. 票價：單程票費用為每段次新台幣$20元，使用悠遊卡可享折扣優惠。此外，台北捷運提供多種定期票供通勤者選擇，如「常客優惠」、「定期票」等。<br>8. 營運時間：週一至週四，五、六日及國定假日略有不同。一般來說，首班車約早上6點發車，末班車則約晚上12點左右。詳細時刻表可參考台北捷運官網。<br>9. 注意事項：進站時需刷卡或購票，出站時再刷一次卡片。禁止飲食、吸菸、攜帶危險物品等。<br>希望以上資訊能幫助你在台北順利地利用捷運系統。祝你旅途愉快！ |
|
| 127 |
+
|
| 128 |
+
</details>
|
| 129 |
+
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
## Features
|
| 133 |
+
|
| 134 |
+
- Expanding the vocabulary dictionary size from 32k to 62k to better support Traditional Chinese
|
| 135 |
+
- 8k-token context length
|
| 136 |
+
- Multi-turn dialogue (without special handling for harmfulness)
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Inference Performance
|
| 140 |
+
In this test, we use the first 700 characters of the [web article](https://health.udn.com/health/story/5976/7699252?from=udn_ch1005_main_index) as the input and ask the model to write the same article again.
|
| 141 |
+
All inferences run on 4 RTX A6000 GPUs (using `vllm`, with a tensor-parallel size of 4).
|
| 142 |
+
|
| 143 |
+
| Models | ↓ Inference Time (sec)|Estimated Max Input Length (Char)|
|
| 144 |
+
|--------------------------------------------------------------------|-------------------|--------------------------|
|
| 145 |
+
| **Breexe-8x7B-Instruct-v0.1** | 27.83 | 11.1k |
|
| 146 |
+
| Mixtral-8x7B-Instruct-v0.1 | 59.49 | 5.1k |
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
## Chat Model Performance
|
| 150 |
+
|
| 151 |
+
**TMMLU+**, **Table**, and **MT-Bench-tw** source from [MediaTek-Research/TCEval-v2](https://huggingface.co/datasets/MediaTek-Research/TCEval-v2),
|
| 152 |
+
which derives from [TCEval-v1](https://github.com/mtkresearch/MR-Models/tree/main/TC-Eval)
|
| 153 |
+
and [ikala/tmmluplus](https://huggingface.co/datasets/ikala/tmmluplus).
|
| 154 |
+
**MMLU** sources from [hails/mmlu_no_train](https://huggingface.co/datasets/hails/mmlu_no_train).
|
| 155 |
+
**MT-Bench** source from [lmsys/mt_bench_human_judgments](https://huggingface.co/datasets/lmsys/mt_bench_human_judgments).
|
| 156 |
+
We use [the code](https://github.com/mtkresearch/TCEval) revised from [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate **TMMLU+**, **Table**, and **MMLU**. All choice problems adapt the selection by the log-likelihood.
|
| 157 |
+
We use [the code](https://github.com/mtkresearch/TCEval) revised from [fastchat llm_judge](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) (GPT4 as judge) to evaluate **MT-Bench-tw** and **MT-Bench**.
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
| Models | |↑ MT-Bench-tw (Score)| TMMLU+ (ACC)|TTQA (ACC) | Table (ACC)| MT-Bench (Score)| MMLU (ACC) |
|
| 161 |
+
|---------------------------------------------------------------------------------------------------------|--------|--------------------|--------------|-------------|-------------|------------------|-------------|
|
| 162 |
+
| | |TC, Chat |TC, Knowledge |TC, Knowledge|TC, Reasoning|EN, Chat |EN, Knowledge|
|
| 163 |
+
| | |0 shot | 0 shot |0 shot | 0 shot |0 shot | 0 shot |
|
| 164 |
+
| [**Breexe-8x7B-Instruct-v0_1**](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-v0_1) | 47B |7.2 | 48.92 | 75.22 | 39.58 | 7.8 | 69.90 |
|
| 165 |
+
| [gpt-3.5-turbo-1106](https://openai.com) | |7.1 | 43.56 | 68.14 | 45.14 |7.9 | 67.09 |
|
| 166 |
+
| [Qwen1.5-14B-Chat](https://huggingface.co/Qwen/Qwen1.5-14B-Chat) | 14B |7.1 | 51.76 | 70.79 | 51.39 |7.8 | 66.65 |
|
| 167 |
+
| [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) | 34B |6.9 | 54.87 | 81.42 | 36.81 |7.6 | 71.04 |
|
| 168 |
+
| [Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) | 7B |6.4 | 44.65 | 67.86 | 34.72 |7.6 | 59.54 |
|
| 169 |
+
| [Breeze-7B-Instruct-v0_1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0_1) | 7B |5.7 | 41.61 | 65.49 | 45.83 |7.1 | 63.26 |
|
| 170 |
+
| [Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) | 6B |5.0 | 44.79 | 72.57 | 25.69 |6.0 | 59.45 |
|
| 171 |
+
| [Taiwan-LLM-13B-v2.0-chat](https://huggingface.co/yentinglin/Taiwan-LLM-13B-v2.0-chat) | 13B |5.0 | 29.47 | 67.26 | 23.61 |N/A* | 50.50 |
|
| 172 |
+
| [Taiwan-LLM-7B-v2.1-chat](https://huggingface.co/yentinglin/Taiwan-LLM-7B-v2.1-chat) | 7B |4.2 | 28.08 | 51.33 | 31.25 |N/A* | 42.72 |
|
| 173 |
+
|
| 174 |
+
\* Taiwan-LLM models responds to multi-turn questions (English) in Traditional Chinese.
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
## Base Model Performance
|
| 178 |
+
|
| 179 |
+
**TMMLU+** and **Table** source from [MediaTek-Research/TCEval-v2](https://huggingface.co/datasets/MediaTek-Research/TCEval-v2),
|
| 180 |
+
which derives from [TCEval-v1](https://github.com/mtkresearch/MR-Models/tree/main/TC-Eval)
|
| 181 |
+
and [ikala/tmmluplus](https://huggingface.co/datasets/ikala/tmmluplus).
|
| 182 |
+
**MMLU** sources from [hails/mmlu_no_train](https://huggingface.co/datasets/hails/mmlu_no_train).
|
| 183 |
+
We use [the code](https://github.com/mtkresearch/TCEval) revised from [EleutherAI/lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate **TMMLU+**, **Table**, and **MMLU**. All choice problems adapt the selection by the log-likelihood.
|
| 184 |
+
|
| 185 |
+
|
| 186 |
+
| Models | |↑ TMMLU+ (ACC)| TTQA (ACC) | Table (ACC) | MMLU (ACC) |
|
| 187 |
+
|-------------------------------------------------------------------------------------|------|--------------|-------------|-------------|-------------|
|
| 188 |
+
| | |TC, Knowledge |TC, Knowledge|TC, Reasoning|EN, Knowledge|
|
| 189 |
+
| | | 5 shot |5 shot | 5 shot | 5 shot |
|
| 190 |
+
| [Yi-34B](https://huggingface.co/01-ai/Yi-34B) | 34B | 63.10 | 87.61 | 49.31 | 77.42 |
|
| 191 |
+
| [Qwen1.5-14B](https://huggingface.co/Qwen/Qwen1.5-14B) | 14B | 54.30 | 78.76 | 54.86 | 70.17 |
|
| 192 |
+
| **Breexe-8x7B-Base-v0_1** | 47B | 50.20 | 79.65 | 39.58 | 70.79 |
|
| 193 |
+
| [Yi-6B](https://huggingface.co/01-ai/Yi-6B) | 6B | 49.63 | 75.22 | 34.72 | 65.35 |
|
| 194 |
+
| [Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) | 7B | 46.51 | 69.03 | 33.33 | 63.14 |
|
| 195 |
+
| [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) | 47B | 46.10 | 64.60 | 47.22 | 72.94 |
|
| 196 |
+
| [Breeze-7B-Base-v0_1](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0_1) | 7B | 40.35 | 68.14 | 28.47 | 61.63 |
|
| 197 |
+
| [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 7B | 36.93 | 53.10 | 27.78 | 64.89 |
|
| 198 |
+
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
|
| 202 |
+
## Use in Transformers
|
| 203 |
+
|
| 204 |
+
First install direct dependencies:
|
| 205 |
+
```
|
| 206 |
+
pip install transformers torch accelerate
|
| 207 |
+
```
|
| 208 |
+
If you want faster inference using flash-attention2, you need to install these dependencies:
|
| 209 |
+
```bash
|
| 210 |
+
pip install packaging ninja
|
| 211 |
+
pip install flash-attn
|
| 212 |
+
```
|
| 213 |
+
Then load the model in transformers:
|
| 214 |
+
```python
|
| 215 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 216 |
+
import torch
|
| 217 |
+
|
| 218 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 219 |
+
"MediaTek-Research/Breexe-8x7B-Instruct-v0_1",
|
| 220 |
+
device_map="auto",
|
| 221 |
+
torch_dtype=torch.bfloat16,
|
| 222 |
+
attn_implementation="flash_attention_2" # optional
|
| 223 |
+
)
|
| 224 |
+
```
|
| 225 |
+
|
| 226 |
+
The structure of the query is
|
| 227 |
+
```txt
|
| 228 |
+
<s> SYS_PROMPT [INST] QUERY1 [/INST] RESPONSE1 [INST] QUERY2 [/INST]
|
| 229 |
+
```
|
| 230 |
+
where `SYS_PROMPT`, `QUERY1`, `RESPONSE1`, and `QUERY2` can be provided by the user.
|
| 231 |
+
|
| 232 |
+
The suggested default `SYS_PROMPT` is
|
| 233 |
+
```txt
|
| 234 |
+
You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.
|
| 235 |
+
```
|
| 236 |
+
|
| 237 |
+
We also integrate `chat_template` into [tokenizer_config.json](tokenizer_config.json), so you can `apply_chat_template` to get the prompt.
|
| 238 |
+
|
| 239 |
+
```python
|
| 240 |
+
>>> from transformers import AutoTokenizer
|
| 241 |
+
>>> tokenizer = AutoTokenizer.from_pretrained("MediaTek-Research/Breexe-8x7B-Instruct-v0_1")
|
| 242 |
+
>>> chat = [
|
| 243 |
+
... {"role": "user", "content": "你好，請問你可以完成什麼任務？"},
|
| 244 |
+
... {"role": "assistant", "content": "你好，我可以幫助您解決各種問題、提供資訊和協助您完成許多不同的任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。"},
|
| 245 |
+
... {"role": "user", "content": "太棒了！"},
|
| 246 |
+
... ]
|
| 247 |
+
>>> tokenizer.apply_chat_template(chat, tokenize=False)
|
| 248 |
+
"<s>You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan. [INST] 你好，請問你可以完成什麼任務？ [/INST] 你好，我可以幫助您解決各種問題、提供資訊和協助您完成許多不同的任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。 [INST] 太棒了！ [/INST] "
|
| 249 |
+
# Tokenized results
|
| 250 |
+
# ['▁', '你好', '，', '請問', '你', '可以', '完成', '什麼', '任務', '？']
|
| 251 |
+
# ['▁', '你好', '，', '我', '可以', '幫助', '您', '解決', '各種', '問題', '、', '提供', '資訊', '和', '協助', '您', '完成', '許多', '不同', '的', '任務', '。', '例如', '：', '回答', '技術', '問題', '、', '提供', '建議', '、', '翻譯', '文字', '、', '尋找', '資料', '或', '協助', '您', '安排', '行程', '等', '。', '請', '告訴', '我', '如何', '能', '幫助', '您', '。']
|
| 252 |
+
# ['▁', '太', '棒', '了', '！']
|
| 253 |
+
```
|
| 254 |
+
|
| 255 |
+
## Citation
|
| 256 |
+
|
| 257 |
+
```
|
| 258 |
+
@article{breexe8x7b2024,
|
| 259 |
+
title={},
|
| 260 |
+
author={},
|
| 261 |
+
journal={arXiv},
|
| 262 |
+
year={2024}
|
| 263 |
+
}
|
| 264 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<EOD>": 61873,
|
| 3 |
+
"<PAD>": 61874
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MixtralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 14336,
|
| 12 |
+
"max_position_embeddings": 32768,
|
| 13 |
+
"model_type": "mixtral",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_experts_per_tok": 2,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"num_local_experts": 8,
|
| 19 |
+
"output_router_logits": true,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"router_aux_loss_coef": 0.02,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.36.2",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 61952
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"transformers_version": "4.36.2",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
pytorch_model-00001-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70b99124c7f5ad492a93d7db50e3a89f656ca6a5df3f22a1f45db6f854d7055b
|
| 3 |
+
size 4903306308
|
pytorch_model-00002-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b88fbef2c6d3454000eb7985c4b165b2bacda21612219a15a0167e4ff53300
|
| 3 |
+
size 4983016612
|
pytorch_model-00003-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f95cd7307dffbefc8de015c0f4ec4d8e64157df8b04c4aa8cb3fcc3119cf7c4e
|
| 3 |
+
size 4899046246
|
pytorch_model-00004-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc43de613b66259a983fc83f759f7b31ff185f2feb42d7f2f57ef644beb7a159
|
| 3 |
+
size 4983016648
|
pytorch_model-00005-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99562c6491a8fcba83e48241083617d1b9f6a87a9d33b032d422ba289b01e2ee
|
| 3 |
+
size 4983016624
|
pytorch_model-00006-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdd72f5d9cb0f4067aee4f9f8dbc1cacd0e651dbabfc8f0c180c9cc5c52442aa
|
| 3 |
+
size 4983016660
|
pytorch_model-00007-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee937ec3ec70bb668503adf912de47153259c79bd744a4fa73f2bc67581611ee
|
| 3 |
+
size 4899046246
|
pytorch_model-00008-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71f1034b3546f9ecf905894545c6c898366da5d6bec6236a57ed9e3190250e33
|
| 3 |
+
size 4983016724
|
pytorch_model-00009-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:336fef8eee298270ecff1f2d8ac7394235f124aec1f4a5af5eeeabe1a449c397
|
| 3 |
+
size 4983016676
|
pytorch_model-00010-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab6fa728ecac0fcb781995f0e450ace523c27726759af222945d107e4297f92b
|
| 3 |
+
size 4899046246
|
pytorch_model-00011-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bee0df2a25c7bdc65921906002830b9a211f0ff1023b304383a4567ecd438628
|
| 3 |
+
size 4983016736
|
pytorch_model-00012-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8a24b43ffe565743cae473d2cae5608f9e6b11ca52af64882fbd031ea25adcd
|
| 3 |
+
size 4983016676
|
pytorch_model-00013-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cfe7d00849c7210e0c81abccce0c123c3b55725fd28f45cbef52169c47f6228
|
| 3 |
+
size 4983016760
|
pytorch_model-00014-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3b46240351c6983690ad9423147a3339ea1fb6c85365d3979ca708514971447
|
| 3 |
+
size 4899046246
|
pytorch_model-00015-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38f4af3e578461abd8e8f2425dcaf0f518095c34bd46ec541e7900eec5d94010
|
| 3 |
+
size 4983016712
|
pytorch_model-00016-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a62a07f984453dfa39d4031806cc092dc3495844b78ee8afa4d7b46de4597379
|
| 3 |
+
size 4983016676
|
pytorch_model-00017-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:435b70b374a35aed13fd4bb2336b484b23b3a381e4b08c8c1c40dd5d09fce3fd
|
| 3 |
+
size 4899046246
|
pytorch_model-00018-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c73a6be22eead9c183166b213d0bb9e0502522c9ae41fe6ddd082c72adae5a
|
| 3 |
+
size 4983016736
|
pytorch_model-00019-of-00019.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a84a394c8ce5f4ac464d10ea35d25ec4a46fbf63431deb56609e8e9a63113278
|
| 3 |
+
size 4701937706
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,1002 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 93896318976
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00019-of-00019.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00019.bin",
|
| 8 |
+
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 9 |
+
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 10 |
+
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 11 |
+
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 12 |
+
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 13 |
+
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 14 |
+
"model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 15 |
+
"model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 16 |
+
"model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 17 |
+
"model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 18 |
+
"model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 19 |
+
"model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 20 |
+
"model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 21 |
+
"model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 22 |
+
"model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 23 |
+
"model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 24 |
+
"model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 25 |
+
"model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 26 |
+
"model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 27 |
+
"model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 28 |
+
"model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 29 |
+
"model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 30 |
+
"model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 31 |
+
"model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 32 |
+
"model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin",
|
| 33 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00019.bin",
|
| 34 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00019.bin",
|
| 35 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 36 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 37 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 39 |
+
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 40 |
+
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 41 |
+
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 42 |
+
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 43 |
+
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 44 |
+
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 45 |
+
"model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 46 |
+
"model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 47 |
+
"model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 48 |
+
"model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00019.bin",
|
| 49 |
+
"model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00019.bin",
|
| 50 |
+
"model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00019.bin",
|
| 51 |
+
"model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 52 |
+
"model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 53 |
+
"model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 54 |
+
"model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 55 |
+
"model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 56 |
+
"model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 57 |
+
"model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 58 |
+
"model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 59 |
+
"model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 60 |
+
"model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 61 |
+
"model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 62 |
+
"model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 63 |
+
"model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00019.bin",
|
| 64 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
|
| 65 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
|
| 66 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 67 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 68 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 69 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00019.bin",
|
| 70 |
+
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 71 |
+
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 72 |
+
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 73 |
+
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 74 |
+
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 75 |
+
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 76 |
+
"model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 77 |
+
"model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 78 |
+
"model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 79 |
+
"model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 80 |
+
"model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 81 |
+
"model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 82 |
+
"model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 83 |
+
"model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 84 |
+
"model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 85 |
+
"model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 86 |
+
"model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 87 |
+
"model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 88 |
+
"model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 89 |
+
"model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 90 |
+
"model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 91 |
+
"model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 92 |
+
"model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 93 |
+
"model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 94 |
+
"model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin",
|
| 95 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00007-of-00019.bin",
|
| 96 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00007-of-00019.bin",
|
| 97 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 98 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 99 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 100 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 101 |
+
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 102 |
+
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 103 |
+
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 104 |
+
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 105 |
+
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 106 |
+
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 107 |
+
"model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 108 |
+
"model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 109 |
+
"model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 110 |
+
"model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 111 |
+
"model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 112 |
+
"model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 113 |
+
"model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 114 |
+
"model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 115 |
+
"model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 116 |
+
"model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00019.bin",
|
| 117 |
+
"model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00019.bin",
|
| 118 |
+
"model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00019.bin",
|
| 119 |
+
"model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 120 |
+
"model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 121 |
+
"model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 122 |
+
"model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 123 |
+
"model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 124 |
+
"model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 125 |
+
"model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00019.bin",
|
| 126 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
|
| 127 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
|
| 128 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00007-of-00019.bin",
|
| 129 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00007-of-00019.bin",
|
| 130 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00007-of-00019.bin",
|
| 131 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00007-of-00019.bin",
|
| 132 |
+
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 133 |
+
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 134 |
+
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 135 |
+
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 136 |
+
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 137 |
+
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 138 |
+
"model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 139 |
+
"model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 140 |
+
"model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 141 |
+
"model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 142 |
+
"model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 143 |
+
"model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 144 |
+
"model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 145 |
+
"model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 146 |
+
"model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 147 |
+
"model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 148 |
+
"model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 149 |
+
"model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 150 |
+
"model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 151 |
+
"model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 152 |
+
"model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 153 |
+
"model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 154 |
+
"model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 155 |
+
"model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 156 |
+
"model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin",
|
| 157 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00008-of-00019.bin",
|
| 158 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00008-of-00019.bin",
|
| 159 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 160 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 161 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 162 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 163 |
+
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 164 |
+
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 165 |
+
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 166 |
+
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 167 |
+
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 168 |
+
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 169 |
+
"model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 170 |
+
"model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 171 |
+
"model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00019.bin",
|
| 172 |
+
"model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00019.bin",
|
| 173 |
+
"model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00019.bin",
|
| 174 |
+
"model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 175 |
+
"model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 176 |
+
"model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 177 |
+
"model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 178 |
+
"model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 179 |
+
"model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 180 |
+
"model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 181 |
+
"model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 182 |
+
"model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 183 |
+
"model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 184 |
+
"model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 185 |
+
"model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 186 |
+
"model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 187 |
+
"model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00019.bin",
|
| 188 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
|
| 189 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
|
| 190 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 191 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 192 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 193 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00008-of-00019.bin",
|
| 194 |
+
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 195 |
+
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 196 |
+
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 197 |
+
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 198 |
+
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 199 |
+
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 200 |
+
"model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 201 |
+
"model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 202 |
+
"model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 203 |
+
"model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 204 |
+
"model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 205 |
+
"model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 206 |
+
"model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 207 |
+
"model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 208 |
+
"model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 209 |
+
"model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 210 |
+
"model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 211 |
+
"model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 212 |
+
"model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 213 |
+
"model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 214 |
+
"model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 215 |
+
"model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 216 |
+
"model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 217 |
+
"model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 218 |
+
"model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin",
|
| 219 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00009-of-00019.bin",
|
| 220 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00009-of-00019.bin",
|
| 221 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 222 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 223 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 224 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 225 |
+
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 226 |
+
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00019.bin",
|
| 227 |
+
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00019.bin",
|
| 228 |
+
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00019.bin",
|
| 229 |
+
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 230 |
+
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 231 |
+
"model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 232 |
+
"model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 233 |
+
"model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 234 |
+
"model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 235 |
+
"model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 236 |
+
"model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 237 |
+
"model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 238 |
+
"model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 239 |
+
"model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 240 |
+
"model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 241 |
+
"model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 242 |
+
"model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 243 |
+
"model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 244 |
+
"model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 245 |
+
"model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 246 |
+
"model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 247 |
+
"model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 248 |
+
"model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 249 |
+
"model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00019.bin",
|
| 250 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00010-of-00019.bin",
|
| 251 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00010-of-00019.bin",
|
| 252 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 253 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 254 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 255 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00009-of-00019.bin",
|
| 256 |
+
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 257 |
+
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 258 |
+
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 259 |
+
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 260 |
+
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 261 |
+
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 262 |
+
"model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 263 |
+
"model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 264 |
+
"model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 265 |
+
"model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 266 |
+
"model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 267 |
+
"model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 268 |
+
"model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 269 |
+
"model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 270 |
+
"model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 271 |
+
"model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 272 |
+
"model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 273 |
+
"model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 274 |
+
"model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00019.bin",
|
| 275 |
+
"model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00019.bin",
|
| 276 |
+
"model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00019.bin",
|
| 277 |
+
"model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 278 |
+
"model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 279 |
+
"model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 280 |
+
"model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00019.bin",
|
| 281 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
|
| 282 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
|
| 283 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00010-of-00019.bin",
|
| 284 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00010-of-00019.bin",
|
| 285 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00010-of-00019.bin",
|
| 286 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00010-of-00019.bin",
|
| 287 |
+
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 288 |
+
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 289 |
+
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 290 |
+
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 291 |
+
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 292 |
+
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 293 |
+
"model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 294 |
+
"model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 295 |
+
"model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 296 |
+
"model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 297 |
+
"model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 298 |
+
"model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 299 |
+
"model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 300 |
+
"model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 301 |
+
"model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 302 |
+
"model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 303 |
+
"model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 304 |
+
"model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 305 |
+
"model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 306 |
+
"model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 307 |
+
"model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 308 |
+
"model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 309 |
+
"model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 310 |
+
"model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 311 |
+
"model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin",
|
| 312 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00011-of-00019.bin",
|
| 313 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00011-of-00019.bin",
|
| 314 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 315 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 316 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 317 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 318 |
+
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 319 |
+
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 320 |
+
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 321 |
+
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 322 |
+
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 323 |
+
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 324 |
+
"model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 325 |
+
"model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 326 |
+
"model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 327 |
+
"model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 328 |
+
"model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 329 |
+
"model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00019.bin",
|
| 330 |
+
"model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00019.bin",
|
| 331 |
+
"model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00019.bin",
|
| 332 |
+
"model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 333 |
+
"model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 334 |
+
"model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 335 |
+
"model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 336 |
+
"model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 337 |
+
"model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 338 |
+
"model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 339 |
+
"model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 340 |
+
"model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 341 |
+
"model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 342 |
+
"model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00019.bin",
|
| 343 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
|
| 344 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
|
| 345 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 346 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 347 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 348 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00011-of-00019.bin",
|
| 349 |
+
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 350 |
+
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 351 |
+
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 352 |
+
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 353 |
+
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 354 |
+
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 355 |
+
"model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 356 |
+
"model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 357 |
+
"model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 358 |
+
"model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 359 |
+
"model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 360 |
+
"model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 361 |
+
"model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 362 |
+
"model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 363 |
+
"model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 364 |
+
"model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 365 |
+
"model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 366 |
+
"model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 367 |
+
"model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 368 |
+
"model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 369 |
+
"model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 370 |
+
"model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 371 |
+
"model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 372 |
+
"model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 373 |
+
"model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin",
|
| 374 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00012-of-00019.bin",
|
| 375 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00012-of-00019.bin",
|
| 376 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 377 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 378 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 379 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 380 |
+
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 381 |
+
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 382 |
+
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 383 |
+
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 384 |
+
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 385 |
+
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 386 |
+
"model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 387 |
+
"model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 388 |
+
"model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 389 |
+
"model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 390 |
+
"model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 391 |
+
"model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 392 |
+
"model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 393 |
+
"model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 394 |
+
"model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 395 |
+
"model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 396 |
+
"model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 397 |
+
"model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 398 |
+
"model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 399 |
+
"model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 400 |
+
"model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 401 |
+
"model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 402 |
+
"model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 403 |
+
"model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 404 |
+
"model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin",
|
| 405 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00019.bin",
|
| 406 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00019.bin",
|
| 407 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 408 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 409 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 410 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 411 |
+
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 412 |
+
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 413 |
+
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 414 |
+
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 415 |
+
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00019.bin",
|
| 416 |
+
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00019.bin",
|
| 417 |
+
"model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00019.bin",
|
| 418 |
+
"model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 419 |
+
"model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 420 |
+
"model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 421 |
+
"model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 422 |
+
"model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 423 |
+
"model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 424 |
+
"model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 425 |
+
"model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 426 |
+
"model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 427 |
+
"model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 428 |
+
"model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 429 |
+
"model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 430 |
+
"model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 431 |
+
"model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 432 |
+
"model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 433 |
+
"model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 434 |
+
"model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 435 |
+
"model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00019.bin",
|
| 436 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
|
| 437 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
|
| 438 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 439 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 440 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 441 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00012-of-00019.bin",
|
| 442 |
+
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 443 |
+
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 444 |
+
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 445 |
+
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 446 |
+
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 447 |
+
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 448 |
+
"model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 449 |
+
"model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 450 |
+
"model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 451 |
+
"model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 452 |
+
"model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 453 |
+
"model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 454 |
+
"model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 455 |
+
"model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 456 |
+
"model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 457 |
+
"model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 458 |
+
"model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 459 |
+
"model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 460 |
+
"model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 461 |
+
"model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 462 |
+
"model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 463 |
+
"model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00019.bin",
|
| 464 |
+
"model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00019.bin",
|
| 465 |
+
"model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00019.bin",
|
| 466 |
+
"model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin",
|
| 467 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00013-of-00019.bin",
|
| 468 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00013-of-00019.bin",
|
| 469 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 470 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 471 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 472 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 473 |
+
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 474 |
+
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 475 |
+
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 476 |
+
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 477 |
+
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 478 |
+
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 479 |
+
"model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 480 |
+
"model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 481 |
+
"model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 482 |
+
"model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 483 |
+
"model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 484 |
+
"model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 485 |
+
"model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 486 |
+
"model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 487 |
+
"model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 488 |
+
"model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 489 |
+
"model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 490 |
+
"model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 491 |
+
"model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 492 |
+
"model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 493 |
+
"model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 494 |
+
"model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 495 |
+
"model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 496 |
+
"model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 497 |
+
"model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00019.bin",
|
| 498 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00014-of-00019.bin",
|
| 499 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00014-of-00019.bin",
|
| 500 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 501 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 502 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 503 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00013-of-00019.bin",
|
| 504 |
+
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 505 |
+
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 506 |
+
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 507 |
+
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 508 |
+
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 509 |
+
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 510 |
+
"model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 511 |
+
"model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 512 |
+
"model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 513 |
+
"model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 514 |
+
"model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 515 |
+
"model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 516 |
+
"model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 517 |
+
"model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 518 |
+
"model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00019.bin",
|
| 519 |
+
"model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00019.bin",
|
| 520 |
+
"model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00019.bin",
|
| 521 |
+
"model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 522 |
+
"model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 523 |
+
"model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 524 |
+
"model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 525 |
+
"model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 526 |
+
"model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 527 |
+
"model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 528 |
+
"model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00019.bin",
|
| 529 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
|
| 530 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
|
| 531 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00014-of-00019.bin",
|
| 532 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00014-of-00019.bin",
|
| 533 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00014-of-00019.bin",
|
| 534 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00014-of-00019.bin",
|
| 535 |
+
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 536 |
+
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 537 |
+
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 538 |
+
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 539 |
+
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 540 |
+
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 541 |
+
"model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 542 |
+
"model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 543 |
+
"model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 544 |
+
"model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 545 |
+
"model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 546 |
+
"model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 547 |
+
"model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 548 |
+
"model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 549 |
+
"model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 550 |
+
"model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 551 |
+
"model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 552 |
+
"model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 553 |
+
"model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 554 |
+
"model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 555 |
+
"model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 556 |
+
"model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 557 |
+
"model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 558 |
+
"model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 559 |
+
"model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin",
|
| 560 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00015-of-00019.bin",
|
| 561 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00015-of-00019.bin",
|
| 562 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 563 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 564 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 565 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 566 |
+
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 567 |
+
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 568 |
+
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 569 |
+
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 570 |
+
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 571 |
+
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 572 |
+
"model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 573 |
+
"model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00019.bin",
|
| 574 |
+
"model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00019.bin",
|
| 575 |
+
"model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00019.bin",
|
| 576 |
+
"model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 577 |
+
"model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 578 |
+
"model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 579 |
+
"model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 580 |
+
"model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 581 |
+
"model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 582 |
+
"model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 583 |
+
"model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 584 |
+
"model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 585 |
+
"model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 586 |
+
"model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 587 |
+
"model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 588 |
+
"model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 589 |
+
"model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 590 |
+
"model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00019.bin",
|
| 591 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
|
| 592 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
|
| 593 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 594 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 595 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 596 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00015-of-00019.bin",
|
| 597 |
+
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 598 |
+
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 599 |
+
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 600 |
+
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 601 |
+
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 602 |
+
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 603 |
+
"model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 604 |
+
"model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 605 |
+
"model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 606 |
+
"model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 607 |
+
"model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 608 |
+
"model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 609 |
+
"model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 610 |
+
"model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 611 |
+
"model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 612 |
+
"model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 613 |
+
"model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 614 |
+
"model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 615 |
+
"model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 616 |
+
"model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 617 |
+
"model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 618 |
+
"model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 619 |
+
"model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 620 |
+
"model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 621 |
+
"model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin",
|
| 622 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00016-of-00019.bin",
|
| 623 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00016-of-00019.bin",
|
| 624 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 625 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 626 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 627 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 628 |
+
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00019.bin",
|
| 629 |
+
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00019.bin",
|
| 630 |
+
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00019.bin",
|
| 631 |
+
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 632 |
+
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 633 |
+
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 634 |
+
"model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 635 |
+
"model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 636 |
+
"model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 637 |
+
"model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 638 |
+
"model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 639 |
+
"model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 640 |
+
"model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 641 |
+
"model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 642 |
+
"model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 643 |
+
"model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 644 |
+
"model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 645 |
+
"model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 646 |
+
"model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 647 |
+
"model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 648 |
+
"model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 649 |
+
"model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 650 |
+
"model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 651 |
+
"model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 652 |
+
"model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00019.bin",
|
| 653 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00017-of-00019.bin",
|
| 654 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00017-of-00019.bin",
|
| 655 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 656 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 657 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 658 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00016-of-00019.bin",
|
| 659 |
+
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 660 |
+
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 661 |
+
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 662 |
+
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 663 |
+
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 664 |
+
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 665 |
+
"model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 666 |
+
"model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 667 |
+
"model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 668 |
+
"model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 669 |
+
"model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 670 |
+
"model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 671 |
+
"model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 672 |
+
"model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 673 |
+
"model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 674 |
+
"model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 675 |
+
"model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 676 |
+
"model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00019.bin",
|
| 677 |
+
"model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00019.bin",
|
| 678 |
+
"model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00019.bin",
|
| 679 |
+
"model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 680 |
+
"model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 681 |
+
"model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 682 |
+
"model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 683 |
+
"model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00019.bin",
|
| 684 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
|
| 685 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
|
| 686 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00017-of-00019.bin",
|
| 687 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00017-of-00019.bin",
|
| 688 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00017-of-00019.bin",
|
| 689 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00017-of-00019.bin",
|
| 690 |
+
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 691 |
+
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 692 |
+
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 693 |
+
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 694 |
+
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 695 |
+
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 696 |
+
"model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 697 |
+
"model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 698 |
+
"model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 699 |
+
"model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 700 |
+
"model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 701 |
+
"model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 702 |
+
"model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 703 |
+
"model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 704 |
+
"model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 705 |
+
"model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 706 |
+
"model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 707 |
+
"model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 708 |
+
"model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 709 |
+
"model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 710 |
+
"model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 711 |
+
"model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 712 |
+
"model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 713 |
+
"model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 714 |
+
"model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin",
|
| 715 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00018-of-00019.bin",
|
| 716 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00018-of-00019.bin",
|
| 717 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 718 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 719 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 720 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 721 |
+
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 722 |
+
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 723 |
+
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00019.bin",
|
| 724 |
+
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00019.bin",
|
| 725 |
+
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00019.bin",
|
| 726 |
+
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 727 |
+
"model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 728 |
+
"model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 729 |
+
"model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 730 |
+
"model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 731 |
+
"model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 732 |
+
"model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 733 |
+
"model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 734 |
+
"model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 735 |
+
"model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 736 |
+
"model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 737 |
+
"model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 738 |
+
"model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 739 |
+
"model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 740 |
+
"model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 741 |
+
"model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 742 |
+
"model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 743 |
+
"model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 744 |
+
"model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 745 |
+
"model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00019.bin",
|
| 746 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00019.bin",
|
| 747 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00019.bin",
|
| 748 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 749 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 750 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 751 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00019.bin",
|
| 752 |
+
"model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 753 |
+
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 754 |
+
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 755 |
+
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 756 |
+
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 757 |
+
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 758 |
+
"model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 759 |
+
"model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 760 |
+
"model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 761 |
+
"model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 762 |
+
"model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00019.bin",
|
| 763 |
+
"model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00019.bin",
|
| 764 |
+
"model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00019.bin",
|
| 765 |
+
"model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 766 |
+
"model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 767 |
+
"model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 768 |
+
"model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 769 |
+
"model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 770 |
+
"model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 771 |
+
"model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 772 |
+
"model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 773 |
+
"model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 774 |
+
"model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 775 |
+
"model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 776 |
+
"model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00019.bin",
|
| 777 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00019-of-00019.bin",
|
| 778 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin",
|
| 779 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 780 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 781 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 782 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00018-of-00019.bin",
|
| 783 |
+
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 784 |
+
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 785 |
+
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 786 |
+
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 787 |
+
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 788 |
+
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 789 |
+
"model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 790 |
+
"model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 791 |
+
"model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 792 |
+
"model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 793 |
+
"model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 794 |
+
"model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 795 |
+
"model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 796 |
+
"model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 797 |
+
"model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 798 |
+
"model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 799 |
+
"model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 800 |
+
"model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 801 |
+
"model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 802 |
+
"model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 803 |
+
"model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 804 |
+
"model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00019.bin",
|
| 805 |
+
"model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00019.bin",
|
| 806 |
+
"model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00019.bin",
|
| 807 |
+
"model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00019.bin",
|
| 808 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00019-of-00019.bin",
|
| 809 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00019-of-00019.bin",
|
| 810 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00019-of-00019.bin",
|
| 811 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00019-of-00019.bin",
|
| 812 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00019-of-00019.bin",
|
| 813 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00019-of-00019.bin",
|
| 814 |
+
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 815 |
+
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 816 |
+
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 817 |
+
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 818 |
+
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 819 |
+
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 820 |
+
"model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 821 |
+
"model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 822 |
+
"model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 823 |
+
"model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 824 |
+
"model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 825 |
+
"model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 826 |
+
"model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 827 |
+
"model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 828 |
+
"model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 829 |
+
"model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 830 |
+
"model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 831 |
+
"model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 832 |
+
"model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 833 |
+
"model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00019.bin",
|
| 834 |
+
"model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00019.bin",
|
| 835 |
+
"model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00019.bin",
|
| 836 |
+
"model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 837 |
+
"model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 838 |
+
"model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00019.bin",
|
| 839 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
|
| 840 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
|
| 841 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00019.bin",
|
| 842 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00019.bin",
|
| 843 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00019.bin",
|
| 844 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00019.bin",
|
| 845 |
+
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 846 |
+
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 847 |
+
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 848 |
+
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 849 |
+
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 850 |
+
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 851 |
+
"model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 852 |
+
"model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 853 |
+
"model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 854 |
+
"model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 855 |
+
"model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 856 |
+
"model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 857 |
+
"model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 858 |
+
"model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 859 |
+
"model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 860 |
+
"model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 861 |
+
"model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 862 |
+
"model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 863 |
+
"model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 864 |
+
"model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 865 |
+
"model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 866 |
+
"model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 867 |
+
"model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 868 |
+
"model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 869 |
+
"model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00019.bin",
|
| 870 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00019.bin",
|
| 871 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00019.bin",
|
| 872 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 873 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 874 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 875 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 876 |
+
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 877 |
+
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 878 |
+
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 879 |
+
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 880 |
+
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 881 |
+
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 882 |
+
"model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 883 |
+
"model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 884 |
+
"model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 885 |
+
"model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 886 |
+
"model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 887 |
+
"model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 888 |
+
"model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00019.bin",
|
| 889 |
+
"model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00019.bin",
|
| 890 |
+
"model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00019.bin",
|
| 891 |
+
"model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 892 |
+
"model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 893 |
+
"model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 894 |
+
"model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 895 |
+
"model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 896 |
+
"model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 897 |
+
"model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 898 |
+
"model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 899 |
+
"model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 900 |
+
"model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00019.bin",
|
| 901 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
|
| 902 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
|
| 903 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 904 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 905 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 906 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00019.bin",
|
| 907 |
+
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 908 |
+
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 909 |
+
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 910 |
+
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 911 |
+
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 912 |
+
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 913 |
+
"model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 914 |
+
"model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 915 |
+
"model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 916 |
+
"model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 917 |
+
"model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 918 |
+
"model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 919 |
+
"model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 920 |
+
"model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 921 |
+
"model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 922 |
+
"model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 923 |
+
"model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 924 |
+
"model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 925 |
+
"model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 926 |
+
"model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 927 |
+
"model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 928 |
+
"model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 929 |
+
"model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 930 |
+
"model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 931 |
+
"model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin",
|
| 932 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00019.bin",
|
| 933 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00019.bin",
|
| 934 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 935 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 936 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 937 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 938 |
+
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 939 |
+
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 940 |
+
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 941 |
+
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 942 |
+
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 943 |
+
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00019.bin",
|
| 944 |
+
"model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00019.bin",
|
| 945 |
+
"model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00019.bin",
|
| 946 |
+
"model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 947 |
+
"model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 948 |
+
"model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 949 |
+
"model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 950 |
+
"model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 951 |
+
"model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 952 |
+
"model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 953 |
+
"model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 954 |
+
"model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 955 |
+
"model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 956 |
+
"model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 957 |
+
"model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 958 |
+
"model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 959 |
+
"model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 960 |
+
"model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 961 |
+
"model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 962 |
+
"model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00019.bin",
|
| 963 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
|
| 964 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
|
| 965 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 966 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 967 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 968 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00019.bin",
|
| 969 |
+
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 970 |
+
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 971 |
+
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 972 |
+
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 973 |
+
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 974 |
+
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 975 |
+
"model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 976 |
+
"model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 977 |
+
"model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 978 |
+
"model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 979 |
+
"model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 980 |
+
"model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 981 |
+
"model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 982 |
+
"model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 983 |
+
"model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 984 |
+
"model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 985 |
+
"model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 986 |
+
"model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 987 |
+
"model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 988 |
+
"model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 989 |
+
"model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 990 |
+
"model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00019.bin",
|
| 991 |
+
"model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00019.bin",
|
| 992 |
+
"model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00019.bin",
|
| 993 |
+
"model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00019.bin",
|
| 994 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00019.bin",
|
| 995 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00019.bin",
|
| 996 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 997 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 998 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 999 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00006-of-00019.bin",
|
| 1000 |
+
"model.norm.weight": "pytorch_model-00019-of-00019.bin"
|
| 1001 |
+
}
|
| 1002 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130
|
| 3 |
+
size 911034
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"61873": {
|
| 30 |
+
"content": "<EOD>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"61874": {
|
| 38 |
+
"content": "<PAD>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
}
|
| 45 |
+
},
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' %}{% endif %}{{ bos_token }} {{ system_message }} {% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/... or system/user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 48 |
+
"clean_up_tokenization_spaces": false,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"legacy": true,
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "</s>",
|
| 53 |
+
"padding_side": "right",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"spaces_between_special_tokens": false,
|
| 56 |
+
"split_special_tokens": false,
|
| 57 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 58 |
+
"trust_remote_code": true,
|
| 59 |
+
"unk_token": "<unk>",
|
| 60 |
+
"use_default_system_prompt": false,
|
| 61 |
+
"use_fast": true
|
| 62 |
+
}
|