Upload folder using huggingface_hub (#1)

- c8d98c46e15559eabaa1806506ea8bd1478266f46ed70fdcc6c205d0a65464de (c6cd29940112b8f994a8b9328c100d5c9524e82a)
- c52b56310d58ef1d3130df575437e93adde2548b55e8af0f90c95f05cc670384 (a69ac484413f4f296a1e45bda9e5843f563724d0)
- 02edfc937fb9f600e70a2fbae7ebc72973db5cbc173e7c283c9d41cc8a875d7c (50542ddf9592e8225d71c2110c7ccb8af492fa80)
- eb7b9777580f5e544ef5de144c832856065e17721ee2f5072b2442a89b2a1781 (c1d9137e72da7d65f6f9c3e0d39617e0db89105e)
- 5252d7e024877c62007ce9516481e5ae5cf7de6087e75f32d60d4a562c36e205 (72bc73b4b2d9671f32887b2b6bb33863cf8809fa)
- b278e05b9dd9e68b325ba0872d9b0c0762fdcb836de727734afcdee61359466c (5d0f480e0e14f8bc0bba5774439c8fc0b1f8791a)

README.md

@@ -0,0 +1,142 @@
+---
+license: other
+tags:
+- mlx
+extra_gated_prompt: "**Meta Large Language Model Compiler (LLM Compiler) LICENSE AGREEMENT**\n\
+  Version Release Date: 27th June 2024\n“**Agreement**” means the terms and conditions\
+  \ for use, reproduction, distribution and modification of the LLM Compiler Materials\
+  \ set forth herein.\n“**Documentation**” means the specifications, manuals and documentation\
+  \ accompanying the LLM Compiler distributed by Meta at:\n* [https://huggingface.co/facebook/llm-compiler-7b](https://huggingface.co/facebook/llm-compiler-7b)\
+  \ * [https://huggingface.co/facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd)\
+  \ * [https://huggingface.co/facebook/llm-compiler-13b](https://huggingface.co/facebook/llm-compiler-13b)\
+  \ * [https://huggingface.co/facebook/llm-compiler-13b-ftd](https://huggingface.co/facebook/llm-compiler-13b-ftd)\n\
+  “**Licensee**” or “**you**” means you, or your employer or any other person or entity\
+  \ (if you are entering into this Agreement on such person or entity’s behalf), of\
+  \ the age required under applicable laws, rules or regulations to provide legal\
+  \ consent and that has legal authority to bind your employer or such other person\
+  \ or entity if you are entering in this Agreement on their behalf.\n“**Meta Large\
+  \ Language Model Compiler” and “LLM Compiler**” mean the foundational large language\
+  \ models and software and algorithms, including machine-learning model code, trained\
+  \ model weights, inference-enabling code, training-enabling code, fine-tuning enabling\
+  \ code and other elements of the foregoing distributed by Meta at:\n* [https://huggingface.co/facebook/llm-compiler-7b](https://huggingface.co/facebook/llm-compiler-7b)\
+  \ * [https://huggingface.co/facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd)\
+  \ * [https://huggingface.co/facebook/llm-compiler-13b](https://huggingface.co/facebook/llm-compiler-13b)\
+  \ * [https://huggingface.co/facebook/llm-compiler-13b-ftd](https://huggingface.co/facebook/llm-compiler-13b-ftd)\n\
+  “**LLM Compiler Materials**” means, collectively, Meta’s proprietary LLM Compiler\
+  \ and Documentation (and any portion thereof) made available under this Agreement.\n\
+  “**Meta**” or “**we**” means Meta Platforms Ireland Limited (if you are located\
+  \ in or, if you are an entity, your principal place of business is in the EEA or\
+  \ Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or\
+  \ Switzerland). \nBy clicking “I Accept” below or by using or distributing any portion\
+  \ or element of the LLM Compiler Materials, you agree to be bound by this Agreement.\n\
+  1. **License Rights and Redistribution**. \\\n\n  a. <span style=\"text-decoration:underline;\"\
+  >Grant of Rights</span>. You are granted a non-exclusive, worldwide, non-transferable\
+  \ and royalty-free limited license under Meta’s intellectual property or other rights\
+  \ owned by Meta embodied in the LLM Compiler Materials to use, reproduce, distribute,\
+  \ copy, create derivative works of, and make modifications to the LLM Compiler Materials.\
+  \  \n\n  b. <span style=\"text-decoration:underline;\">Redistribution and Use</span>.\
+  \  \n\n    i. If you distribute or make available the LLM Compiler Materials (or\
+  \ any derivative works thereof), or a product or service that uses any of them,\
+  \ including another AI model, you shall (A) provide a copy of this Agreement with\
+  \ any such LLM Compiler Materials; and (B) prominently display “Built with LLM Compiler”\
+  \ on a related website, user interface, blogpost, about page, or product documentation.\
+  \ If you use the LLM Compiler Materials to create, train, fine tune, or otherwise\
+  \ improve an AI model, which is distributed or made available, you shall also include\
+  \ “LLM Compiler” at the beginning of any such AI model name.\n\n    ii. If you receive\
+  \ LLM Compiler Materials, or any derivative works thereof, from a Licensee as part\
+  \ of an integrated end user product, then Section 2 of this Agreement will not apply\
+  \ to you. \n\n    iii. You must retain in all copies of the LLM Compiler Materials\
+  \ that you distribute the following attribution notice within a “Notice” text file\
+  \ distributed as a part of such copies: “LLM Compiler is licensed under the LLM\
+  \ Compiler License, Copyright © Meta Platforms, Inc. All Rights Reserved.”\n\n \
+  \   iv. Your use of the LLM Compiler Materials must comply with applicable laws\
+  \ and regulations (including trade compliance laws and regulations) and adhere to\
+  \ the Acceptable Use Policy for Llama Materials (available at https://llama.meta.com/llama3/use-policy),\
+  \ which is hereby incorporated by reference into this Agreement.\n\n    v. You will\
+  \ not use the LLM Compiler Materials or any output or results of the LLM Compiler\
+  \ Materials to improve any other large language model.  \n\n2. **Additional Commercial\
+  \ Terms**. If, on the LLM Compiler release date, the monthly active users of the\
+  \ products or services made available by or for Licensee, or Licensee’s affiliates,\
+  \ is greater than 700 million monthly active users in the preceding calendar month,\
+  \ you must request a license from Meta, which Meta may grant to you in its sole\
+  \ discretion, and you are not authorized to exercise any of the rights under this\
+  \ Agreement unless or until Meta otherwise expressly grants you such rights.  \n\
+  3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLM COMPILER\
+  \ MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS,\
+  \ WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND,\
+  \ BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE,\
+  \ NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE\
+  \ SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
+  \ THE LLM COMPILER MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE\
+  \ LLM COMPILER MATERIALS AND ANY OUTPUT AND RESULTS.\n4. **Limitation of Liability**.\
+  \ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
+  \ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
+  \ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
+  \ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
+  \ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. **Intellectual Property**.\n\
+  \n  a. No trademark licenses are granted under this Agreement, and in connection\
+  \ with the LLM Compiler Materials, neither Meta nor Licensee may use any name or\
+  \ mark owned by or associated with the other or any of its affiliates, except as\
+  \ required for reasonable and customary use in describing and redistributing the\
+  \ LLM Compiler Materials or as set forth in this Section 5(a). Meta hereby grants\
+  \ you a license to use LLM Compiler  (the “Mark”) solely as required to comply with\
+  \ the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines\
+  \ (currently accessible at[ https://about.meta.com/brand/resources/meta/company-brand/)](https://about.meta.com/brand/resources/meta/company-brand/).\
+  \ All goodwill arising out of your use of the Mark will inure to the benefit of\
+  \ Meta.  \n\n  b. Subject to Meta’s ownership of LLM Compiler Materials and derivatives\
+  \ made by or for Meta, with respect to any derivative works and modifications of\
+  \ the LLM Compiler Materials that are made by you, as between you and Meta, you\
+  \ are and will be the owner of such derivative works and modifications.\n\n  c.\
+  \ If you institute litigation or other proceedings against Meta or any entity (including\
+  \ a cross-claim or counterclaim in a lawsuit) alleging that the LLM Compiler Materials\
+  \ or LLM Compiler outputs or results, or any portion of any of the foregoing, constitutes\
+  \ infringement of intellectual property or other rights owned or licensable by you,\
+  \ then any licenses granted to you under this Agreement shall terminate as of the\
+  \ date such litigation or claim is filed or instituted. You will indemnify and hold\
+  \ harmless Meta from and against any claim by any third party arising out of or\
+  \ related to your use or distribution of the LLM Compiler Materials.\n\n6. **Term\
+  \ and Termination**. The term of this Agreement will commence upon your acceptance\
+  \ of this Agreement or access to the LLM Compiler Materials and will continue in\
+  \ full force and effect until terminated in accordance with the terms and conditions\
+  \ herein. Meta may terminate this Agreement if you are in breach of any term or\
+  \ condition of this Agreement. Upon termination of this Agreement, you shall delete\
+  \ and cease use of the LLM Compiler Materials. Sections 3, 4 and 7 shall survive\
+  \ the termination of this Agreement. \n7. **Governing Law and Jurisdiction**. This\
+  \ Agreement will be governed and construed under the laws of the State of California\
+  \ without regard to choice of law principles, and the UN Convention on Contracts\
+  \ for the International Sale of Goods does not apply to this Agreement. The courts\
+  \ of California shall have exclusive jurisdiction of any dispute arising out of\
+  \ this Agreement. "
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  I accept the terms and conditions: checkbox
+  geo: ip_location
+  ? By clicking Submit below I accept the terms of the license and acknowledge that
+    the information I provide will be collected stored processed and shared in accordance
+    with the Meta Privacy Policy
+  : checkbox
+extra_gated_description: The information you provide will be collected, stored, processed
+  and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
+extra_gated_button_content: I Accept Meta LLM Compiler License and AUP
+---
+
+# typealias/llm-compiler-13b-ftd-mlx
+
+The Model [typealias/llm-compiler-13b-ftd-mlx](https://huggingface.co/typealias/llm-compiler-13b-ftd-mlx) was converted to MLX format from [typealias/llm-compiler-13b-ftd](https://huggingface.co/typealias/llm-compiler-13b-ftd) using mlx-lm version **0.15.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("typealias/llm-compiler-13b-ftd-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,27 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.37.2",
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7d2f582ae76348178f6fa04011df0f0e5a105de6ff4af910491ed8de5df91a
+size 5261381471

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d38443deaac1c1fb9cedb2d6e623be40d0b9f033c4df5020121288245f8cbea
+size 5321716419

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daca9131627c61940e5a41e5b49de76b09f5387d191f4fd4a0f5af6fb3dbc2a0
+size 5321695727

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee80e2a1fdf752fec1802456467ec1a5fcdc50020a1ba13cb9f647f5b39a6e2e
+size 5358416475

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d4e0049ddaf3e0edf915178f1a21d2723b2e7e3a18aa82f20aee06d30ab254
+size 4768560447

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+    "metadata": {
+        "total_size": 26031728640
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00005-of-00005.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.norm.weight": "model-00005-of-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d77173a958615d2779fe7b6771a8e310f6f448715f56038a24c1641f9359a67
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}