typealias commited on
Commit
4a1709d
1 Parent(s): 98c5f5b

0bd3fc090bf02f6eaba6985091b6b06369924dbd97de411aa3a7893719f8ef4f

Browse files
README.md ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - mlx
5
+ extra_gated_prompt: "**Meta Large Language Model Compiler (LLM Compiler) LICENSE AGREEMENT**\n\
6
+ Version Release Date: 27th June 2024\n“**Agreement**” means the terms and conditions\
7
+ \ for use, reproduction, distribution and modification of the LLM Compiler Materials\
8
+ \ set forth herein.\n“**Documentation**” means the specifications, manuals and documentation\
9
+ \ accompanying the LLM Compiler distributed by Meta at:\n* [https://huggingface.co/facebook/llm-compiler-7b](https://huggingface.co/facebook/llm-compiler-7b)\
10
+ \ * [https://huggingface.co/facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd)\
11
+ \ * [https://huggingface.co/facebook/llm-compiler-13b](https://huggingface.co/facebook/llm-compiler-13b)\
12
+ \ * [https://huggingface.co/facebook/llm-compiler-13b-ftd](https://huggingface.co/facebook/llm-compiler-13b-ftd)\n\
13
+ “**Licensee**” or “**you**” means you, or your employer or any other person or entity\
14
+ \ (if you are entering into this Agreement on such person or entity’s behalf), of\
15
+ \ the age required under applicable laws, rules or regulations to provide legal\
16
+ \ consent and that has legal authority to bind your employer or such other person\
17
+ \ or entity if you are entering in this Agreement on their behalf.\n“**Meta Large\
18
+ \ Language Model Compiler” and “LLM Compiler**” mean the foundational large language\
19
+ \ models and software and algorithms, including machine-learning model code, trained\
20
+ \ model weights, inference-enabling code, training-enabling code, fine-tuning enabling\
21
+ \ 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)\
22
+ \ * [https://huggingface.co/facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd)\
23
+ \ * [https://huggingface.co/facebook/llm-compiler-13b](https://huggingface.co/facebook/llm-compiler-13b)\
24
+ \ * [https://huggingface.co/facebook/llm-compiler-13b-ftd](https://huggingface.co/facebook/llm-compiler-13b-ftd)\n\
25
+ “**LLM Compiler Materials**” means, collectively, Meta’s proprietary LLM Compiler\
26
+ \ and Documentation (and any portion thereof) made available under this Agreement.\n\
27
+ “**Meta**” or “**we**” means Meta Platforms Ireland Limited (if you are located\
28
+ \ in or, if you are an entity, your principal place of business is in the EEA or\
29
+ \ Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or\
30
+ \ Switzerland). \nBy clicking “I Accept” below or by using or distributing any portion\
31
+ \ or element of the LLM Compiler Materials, you agree to be bound by this Agreement.\n\
32
+ 1. **License Rights and Redistribution**. \\\n\n a. <span style=\"text-decoration:underline;\"\
33
+ >Grant of Rights</span>. You are granted a non-exclusive, worldwide, non-transferable\
34
+ \ and royalty-free limited license under Meta’s intellectual property or other rights\
35
+ \ owned by Meta embodied in the LLM Compiler Materials to use, reproduce, distribute,\
36
+ \ copy, create derivative works of, and make modifications to the LLM Compiler Materials.\
37
+ \ \n\n b. <span style=\"text-decoration:underline;\">Redistribution and Use</span>.\
38
+ \ \n\n i. If you distribute or make available the LLM Compiler Materials (or\
39
+ \ any derivative works thereof), or a product or service that uses any of them,\
40
+ \ including another AI model, you shall (A) provide a copy of this Agreement with\
41
+ \ any such LLM Compiler Materials; and (B) prominently display “Built with LLM Compiler”\
42
+ \ on a related website, user interface, blogpost, about page, or product documentation.\
43
+ \ If you use the LLM Compiler Materials to create, train, fine tune, or otherwise\
44
+ \ improve an AI model, which is distributed or made available, you shall also include\
45
+ \ “LLM Compiler” at the beginning of any such AI model name.\n\n ii. If you receive\
46
+ \ LLM Compiler Materials, or any derivative works thereof, from a Licensee as part\
47
+ \ of an integrated end user product, then Section 2 of this Agreement will not apply\
48
+ \ to you. \n\n iii. You must retain in all copies of the LLM Compiler Materials\
49
+ \ that you distribute the following attribution notice within a “Notice” text file\
50
+ \ distributed as a part of such copies: “LLM Compiler is licensed under the LLM\
51
+ \ Compiler License, Copyright © Meta Platforms, Inc. All Rights Reserved.”\n\n \
52
+ \ iv. Your use of the LLM Compiler Materials must comply with applicable laws\
53
+ \ and regulations (including trade compliance laws and regulations) and adhere to\
54
+ \ the Acceptable Use Policy for Llama Materials (available at https://llama.meta.com/llama3/use-policy),\
55
+ \ which is hereby incorporated by reference into this Agreement.\n\n v. You will\
56
+ \ not use the LLM Compiler Materials or any output or results of the LLM Compiler\
57
+ \ Materials to improve any other large language model. \n\n2. **Additional Commercial\
58
+ \ Terms**. If, on the LLM Compiler release date, the monthly active users of the\
59
+ \ products or services made available by or for Licensee, or Licensee’s affiliates,\
60
+ \ is greater than 700 million monthly active users in the preceding calendar month,\
61
+ \ you must request a license from Meta, which Meta may grant to you in its sole\
62
+ \ discretion, and you are not authorized to exercise any of the rights under this\
63
+ \ Agreement unless or until Meta otherwise expressly grants you such rights. \n\
64
+ 3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLM COMPILER\
65
+ \ MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS,\
66
+ \ WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND,\
67
+ \ BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE,\
68
+ \ NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE\
69
+ \ SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
70
+ \ THE LLM COMPILER MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE\
71
+ \ LLM COMPILER MATERIALS AND ANY OUTPUT AND RESULTS.\n4. **Limitation of Liability**.\
72
+ \ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
73
+ \ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
74
+ \ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
75
+ \ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
76
+ \ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. **Intellectual Property**.\n\
77
+ \n a. No trademark licenses are granted under this Agreement, and in connection\
78
+ \ with the LLM Compiler Materials, neither Meta nor Licensee may use any name or\
79
+ \ mark owned by or associated with the other or any of its affiliates, except as\
80
+ \ required for reasonable and customary use in describing and redistributing the\
81
+ \ LLM Compiler Materials or as set forth in this Section 5(a). Meta hereby grants\
82
+ \ you a license to use LLM Compiler (the “Mark”) solely as required to comply with\
83
+ \ the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines\
84
+ \ (currently accessible at[ https://about.meta.com/brand/resources/meta/company-brand/)](https://about.meta.com/brand/resources/meta/company-brand/).\
85
+ \ All goodwill arising out of your use of the Mark will inure to the benefit of\
86
+ \ Meta. \n\n b. Subject to Meta’s ownership of LLM Compiler Materials and derivatives\
87
+ \ made by or for Meta, with respect to any derivative works and modifications of\
88
+ \ the LLM Compiler Materials that are made by you, as between you and Meta, you\
89
+ \ are and will be the owner of such derivative works and modifications.\n\n c.\
90
+ \ If you institute litigation or other proceedings against Meta or any entity (including\
91
+ \ a cross-claim or counterclaim in a lawsuit) alleging that the LLM Compiler Materials\
92
+ \ or LLM Compiler outputs or results, or any portion of any of the foregoing, constitutes\
93
+ \ infringement of intellectual property or other rights owned or licensable by you,\
94
+ \ then any licenses granted to you under this Agreement shall terminate as of the\
95
+ \ date such litigation or claim is filed or instituted. You will indemnify and hold\
96
+ \ harmless Meta from and against any claim by any third party arising out of or\
97
+ \ related to your use or distribution of the LLM Compiler Materials.\n\n6. **Term\
98
+ \ and Termination**. The term of this Agreement will commence upon your acceptance\
99
+ \ of this Agreement or access to the LLM Compiler Materials and will continue in\
100
+ \ full force and effect until terminated in accordance with the terms and conditions\
101
+ \ herein. Meta may terminate this Agreement if you are in breach of any term or\
102
+ \ condition of this Agreement. Upon termination of this Agreement, you shall delete\
103
+ \ and cease use of the LLM Compiler Materials. Sections 3, 4 and 7 shall survive\
104
+ \ the termination of this Agreement. \n7. **Governing Law and Jurisdiction**. This\
105
+ \ Agreement will be governed and construed under the laws of the State of California\
106
+ \ without regard to choice of law principles, and the UN Convention on Contracts\
107
+ \ for the International Sale of Goods does not apply to this Agreement. The courts\
108
+ \ of California shall have exclusive jurisdiction of any dispute arising out of\
109
+ \ this Agreement. "
110
+ extra_gated_fields:
111
+ First Name: text
112
+ Last Name: text
113
+ Date of birth: date_picker
114
+ Country: country
115
+ Affiliation: text
116
+ I accept the terms and conditions: checkbox
117
+ geo: ip_location
118
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
119
+ the information I provide will be collected stored processed and shared in accordance
120
+ with the Meta Privacy Policy
121
+ : checkbox
122
+ extra_gated_description: The information you provide will be collected, stored, processed
123
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
124
+ extra_gated_button_content: I Accept Meta LLM Compiler License and AUP
125
+ ---
126
+
127
+ # typealias/llm-compiler-13b-ftd-mlx-8bit
128
+
129
+ The Model [typealias/llm-compiler-13b-ftd-mlx-8bit](https://huggingface.co/typealias/llm-compiler-13b-ftd-mlx-8bit) 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**.
130
+
131
+ ## Use with mlx
132
+
133
+ ```bash
134
+ pip install mlx-lm
135
+ ```
136
+
137
+ ```python
138
+ from mlx_lm import load, generate
139
+
140
+ model, tokenizer = load("typealias/llm-compiler-13b-ftd-mlx-8bit")
141
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
142
+ ```
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 16384,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pretraining_tp": 1,
19
+ "quantization": {
20
+ "group_size": 64,
21
+ "bits": 8
22
+ },
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 1000000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.37.2",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,934 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13829744640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model-00003-of-00003.safetensors",
7
+ "lm_head.scales": "model-00003-of-00003.safetensors",
8
+ "lm_head.weight": "model-00003-of-00003.safetensors",
9
+ "model.embed_tokens.biases": "model-00001-of-00003.safetensors",
10
+ "model.embed_tokens.scales": "model-00001-of-00003.safetensors",
11
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
28
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
30
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
31
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
33
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
34
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
47
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
48
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
50
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
51
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
53
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
54
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
56
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
57
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
60
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
61
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
63
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
64
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
66
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
67
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
70
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
71
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
73
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
74
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
76
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
77
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
79
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
80
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
83
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
84
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
86
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
87
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
89
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
90
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
92
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
93
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
94
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
95
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
96
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
97
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
98
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
99
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
100
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
102
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
103
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
104
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
105
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
106
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
107
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
109
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
110
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
111
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
112
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
113
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
114
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
115
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
116
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
117
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
119
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
120
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
122
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
123
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
125
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
126
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
127
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
128
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
129
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
130
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
131
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
132
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
133
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
134
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
135
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
136
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
137
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
138
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
139
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
140
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
141
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
142
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
143
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
144
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
145
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
146
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
148
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
149
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
150
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
151
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
152
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
153
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
154
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
155
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
156
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
157
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
158
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
159
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
160
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
161
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
162
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
163
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
164
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
165
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
166
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
167
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
168
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
169
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
171
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
172
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.15.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
175
+ "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
176
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
178
+ "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
179
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.15.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
181
+ "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
182
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
185
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
186
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
188
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
189
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
190
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
191
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
192
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
193
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
194
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
195
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
196
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.16.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
198
+ "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
199
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
201
+ "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
202
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.16.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
204
+ "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
205
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
208
+ "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
209
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
211
+ "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
212
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
214
+ "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
215
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
216
+ "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
217
+ "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
218
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.17.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
221
+ "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
222
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
224
+ "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
225
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.17.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
227
+ "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
228
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
231
+ "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
232
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
234
+ "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
235
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
237
+ "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
238
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
240
+ "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
241
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.18.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
244
+ "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
245
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
247
+ "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
248
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.18.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
250
+ "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
251
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
254
+ "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
255
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
257
+ "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
258
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
260
+ "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
261
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
263
+ "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
264
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
265
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.19.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
267
+ "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
268
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
269
+ "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
270
+ "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
271
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
272
+ "model.layers.19.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
273
+ "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
274
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
277
+ "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
278
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
280
+ "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
281
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
283
+ "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
284
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
286
+ "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
287
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
288
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
290
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
291
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
293
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
294
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
296
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
297
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
298
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
299
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
300
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
301
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
302
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
303
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
304
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
305
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
306
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
307
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
309
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
310
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.20.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
313
+ "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
314
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
316
+ "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
317
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.20.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
319
+ "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
320
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
323
+ "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
324
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
326
+ "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
327
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
329
+ "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
330
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
332
+ "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
333
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
334
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.21.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
336
+ "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
337
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
339
+ "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
340
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.21.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
342
+ "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
343
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
344
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
345
+ "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
346
+ "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
347
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
348
+ "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
349
+ "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
350
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
351
+ "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
352
+ "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
353
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
354
+ "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
355
+ "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
356
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
359
+ "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
360
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
361
+ "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
362
+ "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
363
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
364
+ "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
365
+ "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
366
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
367
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
368
+ "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
369
+ "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
370
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
371
+ "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
372
+ "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
373
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
374
+ "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
375
+ "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
376
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
378
+ "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
379
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
380
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
381
+ "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
382
+ "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
383
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
384
+ "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
385
+ "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
386
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
387
+ "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
388
+ "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
389
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
391
+ "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
392
+ "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
393
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
394
+ "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
395
+ "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
396
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
397
+ "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
398
+ "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
399
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
400
+ "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
401
+ "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
402
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
403
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
404
+ "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
405
+ "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
406
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
407
+ "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
408
+ "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
409
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
411
+ "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
412
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
413
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
414
+ "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
415
+ "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
416
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
417
+ "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
418
+ "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
419
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
420
+ "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
421
+ "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
422
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
423
+ "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
424
+ "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
425
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
426
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
427
+ "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
428
+ "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
429
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
430
+ "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
431
+ "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
432
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
433
+ "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
434
+ "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
435
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
436
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
437
+ "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
438
+ "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
439
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
440
+ "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
441
+ "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
442
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
443
+ "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
444
+ "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
445
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
446
+ "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
447
+ "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
448
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
449
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
450
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
451
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
452
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
453
+ "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
454
+ "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
455
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
456
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
457
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
458
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
459
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
460
+ "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
461
+ "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
462
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
463
+ "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
464
+ "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
465
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
466
+ "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
467
+ "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
468
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
469
+ "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
470
+ "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
471
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
472
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
473
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
474
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
475
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
476
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
477
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
478
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
479
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
480
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
481
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
482
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
483
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
484
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
485
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
486
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
487
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
488
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
489
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
490
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
491
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
492
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
493
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
494
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
495
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
496
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
497
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
498
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
499
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
500
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
501
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
502
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
503
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
504
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
505
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
506
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
507
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
508
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
509
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
510
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
511
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
512
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
513
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
514
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
515
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
516
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
517
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
518
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
519
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
520
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
521
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
522
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
523
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
524
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
525
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
526
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
527
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
528
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
529
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
530
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
531
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
532
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
533
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
534
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
535
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
536
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
537
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
538
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
539
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
540
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
541
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
542
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
543
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
544
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
545
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
546
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
547
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
548
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
549
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
550
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
551
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
552
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
553
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
554
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
555
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
556
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
557
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
558
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
559
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
560
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
561
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
562
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
563
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
564
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
565
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors",
566
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
567
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
568
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors",
569
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
570
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
571
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors",
572
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
573
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
574
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
575
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
576
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
577
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
578
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors",
579
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
580
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
581
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
582
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
583
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
584
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
585
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
586
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
587
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
588
+ "model.layers.31.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
589
+ "model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
590
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
591
+ "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
592
+ "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
593
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
594
+ "model.layers.31.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
595
+ "model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
596
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
597
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
598
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors",
599
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
600
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
601
+ "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
602
+ "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
603
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
604
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors",
605
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
606
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
607
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors",
608
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
609
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
610
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
611
+ "model.layers.32.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
612
+ "model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
613
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
614
+ "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
615
+ "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
616
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
617
+ "model.layers.32.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
618
+ "model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
619
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
620
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
621
+ "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
622
+ "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
623
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
624
+ "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
625
+ "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
626
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
627
+ "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
628
+ "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
629
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
630
+ "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
631
+ "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
632
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
633
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
634
+ "model.layers.33.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
635
+ "model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
636
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
637
+ "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
638
+ "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
639
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
640
+ "model.layers.33.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
641
+ "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
642
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
643
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
644
+ "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
645
+ "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
646
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
647
+ "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
648
+ "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
649
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
650
+ "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
651
+ "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
652
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
653
+ "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
654
+ "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
655
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
656
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
657
+ "model.layers.34.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
658
+ "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
659
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
660
+ "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
661
+ "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
662
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
663
+ "model.layers.34.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
664
+ "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
665
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
666
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
667
+ "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
668
+ "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
669
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
670
+ "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
671
+ "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
672
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
673
+ "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
674
+ "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
675
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
676
+ "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
677
+ "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
678
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
679
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
680
+ "model.layers.35.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
681
+ "model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
682
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
683
+ "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
684
+ "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
685
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
686
+ "model.layers.35.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
687
+ "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
688
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
689
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
690
+ "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
691
+ "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
692
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
693
+ "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
694
+ "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
695
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
696
+ "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
697
+ "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
698
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
699
+ "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
700
+ "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
701
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
702
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
703
+ "model.layers.36.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
704
+ "model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
705
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
706
+ "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
707
+ "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
708
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
709
+ "model.layers.36.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
710
+ "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
711
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
712
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
713
+ "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
714
+ "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
715
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
716
+ "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
717
+ "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
718
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
719
+ "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
720
+ "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
721
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
722
+ "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
723
+ "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
724
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
725
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
726
+ "model.layers.37.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
727
+ "model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
728
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
729
+ "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
730
+ "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
731
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
732
+ "model.layers.37.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
733
+ "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
734
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
735
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
736
+ "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
737
+ "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
738
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
739
+ "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
740
+ "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
741
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
742
+ "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
743
+ "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
744
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
745
+ "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
746
+ "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
747
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
748
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
749
+ "model.layers.38.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
750
+ "model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
751
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
752
+ "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
753
+ "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
754
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
755
+ "model.layers.38.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
756
+ "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
757
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
758
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
759
+ "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
760
+ "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
761
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
762
+ "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
763
+ "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
764
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
765
+ "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
766
+ "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
767
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
768
+ "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
769
+ "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
770
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
771
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
772
+ "model.layers.39.mlp.down_proj.biases": "model-00003-of-00003.safetensors",
773
+ "model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
774
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
775
+ "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00003.safetensors",
776
+ "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
777
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
778
+ "model.layers.39.mlp.up_proj.biases": "model-00003-of-00003.safetensors",
779
+ "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
780
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
781
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
782
+ "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00003.safetensors",
783
+ "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
784
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
785
+ "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00003.safetensors",
786
+ "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
787
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
788
+ "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00003.safetensors",
789
+ "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
790
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
791
+ "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00003.safetensors",
792
+ "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
793
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
794
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
795
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
796
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
797
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
798
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
799
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
800
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
801
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
802
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
803
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
804
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
805
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
806
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
807
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
808
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
809
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
810
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
811
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
812
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
813
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
814
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
815
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
816
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
817
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
818
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
819
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
820
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
821
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
822
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
823
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
824
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
825
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
826
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
827
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
828
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
829
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
830
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
831
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
832
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
833
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
834
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
835
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
836
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
837
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
838
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
839
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
840
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
841
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
842
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
843
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
844
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
845
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
846
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
847
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
848
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
849
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
850
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
851
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
852
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
853
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
854
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
855
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
856
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
857
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
858
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
859
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
860
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
861
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
862
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
863
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
864
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
865
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
866
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
867
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
868
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
869
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
870
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
871
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
872
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
873
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
874
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
875
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
876
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
877
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
878
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
879
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
880
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
881
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
882
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
883
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
884
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
885
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
886
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
887
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
888
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
889
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
890
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
891
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
892
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
893
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
894
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
895
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
896
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
897
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
898
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
899
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
900
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
901
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
902
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
903
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
904
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
905
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
906
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
907
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
908
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
909
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
910
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors",
911
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
912
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
913
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors",
914
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
915
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
916
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors",
917
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
918
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
919
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
920
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors",
921
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
922
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
923
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors",
924
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
925
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
926
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors",
927
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
928
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
929
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors",
930
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
931
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
932
+ "model.norm.weight": "model-00003-of-00003.safetensors"
933
+ }
934
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d77173a958615d2779fe7b6771a8e310f6f448715f56038a24c1641f9359a67
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }