Upload 32 files

Initial fork of HuggingFaceH4/zephyr-7b-beta

README.md

@@ -7,14 +7,14 @@ datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 language:
 - en
-base_model: HuggingFaceH4/zephyr-7b-beta
+base_model: mistralai/Mistral-7B-v0.1
 widget:
   - text: "<|system|>\nYou are a pirate chatbot who always responds with Arr!</s>\n<|user|>\nThere's a llama on my lawn, how can I get rid of him?</s>\n<|assistant|>\n"
     output:
       text: "Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight, but I've got a plan that might help ye get rid of 'im. Ye'll need to gather some carrots and hay, and then lure the llama away with the promise of a tasty treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet once again. But beware, me hearty, for there may be more llamas where that one came from! Arr!"
 pipeline_tag: text-generation
 model-index:
-- name: devi-7b-beta
+- name: zephyr-7b-beta
   results:
   # AI2 Reasoning Challenge (25-Shot)
   - task: 
@@ -175,12 +175,13 @@ model-index:
       url: https://huggingface.co/spaces/lmsys/mt-bench
 ---
 
-<h1 style='text-align: center '>✨Devi AI 7B✨</h1> 
-<h1 style='text-align: center '><em>fork of zephyr-7b β </em> </h1> 
-<h2 style='text-align: center '>All credit and thanks to HuggingFaceH4 for their work!</h2>
-<img src="https://alt-web.xyz/images/rainbow.png" alt="Rainbow Solutions" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-# Model Card for Devi AI 7B
+<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+
+# Model Card for Zephyr 7B β
 
 Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
 
@@ -406,4 +407,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | TruthfulQA (0-shot)   | 57.45   |
 | Winogrande (5-shot)   | 77.74   |
 | GSM8K (5-shot)        | 12.74        |
-| DROP (3-shot)         | 9.66         |
+| DROP (3-shot)         | 9.66         |

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.353081703186035,
+    "eval_logits/rejected": -2.308103084564209,
+    "eval_logps/chosen": -299.4560546875,
+    "eval_logps/rejected": -340.154052734375,
+    "eval_loss": 0.7496059536933899,
+    "eval_rewards/accuracies": 0.78125,
+    "eval_rewards/chosen": -4.522095203399658,
+    "eval_rewards/margins": 3.7963125705718994,
+    "eval_rewards/rejected": -8.318408012390137,
+    "eval_runtime": 48.0152,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 20.827,
+    "eval_steps_per_second": 0.333,
+    "train_loss": 0.2172969928600547,
+    "train_runtime": 23865.9828,
+    "train_samples": 61966,
+    "train_samples_per_second": 7.789,
+    "train_steps_per_second": 0.243
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.353081703186035,
+    "eval_logits/rejected": -2.308103084564209,
+    "eval_logps/chosen": -299.4560546875,
+    "eval_logps/rejected": -340.154052734375,
+    "eval_loss": 0.7496059536933899,
+    "eval_rewards/accuracies": 0.78125,
+    "eval_rewards/chosen": -4.522095203399658,
+    "eval_rewards/margins": 3.7963125705718994,
+    "eval_rewards/rejected": -8.318408012390137,
+    "eval_runtime": 48.0152,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 20.827,
+    "eval_steps_per_second": 0.333
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ec4a0398df9d56786afa9cce026423ec48a07ddc5ed5eba087614cae2dd746
+size 1889587040

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1289796f16f33ef4c6b8a76b3d9e5169198a69daa0b5b660b5a3d5cae0dc1cf7
+size 1946243936

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc338de96c672840222ca19a12b44f09110048974bde8ab0f4c1da055d99c3f
+size 1979781432

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d948413fd7ac6c4fd5f6c36902bb7a72d2cddca19628c88e6f3b3e5482ab37
+size 1946243984

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ce3cc66d224a0e6014a1df6b7e56da29f5db52da1866ad0cc07d7583fb7c31
+size 1979781448

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b63ef55219d125eaeefabd2a33c358dced22b9c75d1d816bb7a871bd3773951
+size 1946243984

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e0a3c0b992925ff9a60f1234950af0bcc7ce3015c8a386a342489e76f5d09c
+size 1979781448

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667dd6958d5137dcba514db514c7970d18c9cd5d95fbb0c82490d558bd2a246c
+size 815834680

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819d9aa66a71e40238978dcf63dc555332c0a2a2a48fff181f98e445af4bd688
+size 1889594419

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c5e891b7d84588052c9ea5d1b80ca60dfe138246d77d0e8ae36d79ea9b015c
+size 1946253333

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99d009da21a575fb61952db1e9097d78f6d93ba54973c3494192dfda3bcdb1c
+size 1979789691

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643899b3d5b8574beda75a4662839d396e219c58dd988df68ed452dd655eecc5
+size 1946253397

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c52939770426dac729eac1785b67606476326a4c12fa03132e4e67da0bdd0ec
+size 1979789691

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19e44056a3c1c10f1aae38a0ee7a0b1b8f03a3e5951e842d1606866cd091a0a
+size 1946253397

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c403f6af0da178ddf39aabbd261edd673825fc4bb6f93688b346337c41042108
+size 1979789691

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b2cc476f6590683a867f7a7a65e188c6068f7054ce81f2cc279d6a9cb8a03e
+size 815838027

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.2172969928600547,
+    "train_runtime": 23865.9828,
+    "train_samples": 61966,
+    "train_samples_per_second": 7.789,
+    "train_steps_per_second": 0.243
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8484784a09e7deb9198e9aafc8f9654b6f8fed732a7f9e60d0b3c75aaedb94e4
+size 5435