TheCraftySlayer commited on
Commit
697f0d4
1 Parent(s): 4a18c30

Upload 13 files

Browse files
Llama-2-70b-chat-hf/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Responsible-Use-Guide.pdf filter=lfs diff=lfs merge=lfs -text
Llama-2-70b-chat-hf/LICENSE.txt ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LLAMA 2 COMMUNITY LICENSE AGREEMENT
2
+ Llama 2 Version Release Date: July 18, 2023
3
+
4
+ "Agreement" means the terms and conditions for use, reproduction, distribution and
5
+ modification of the Llama Materials set forth herein.
6
+
7
+ "Documentation" means the specifications, manuals and documentation
8
+ accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
9
+ libraries/llama-downloads/.
10
+
11
+ "Licensee" or "you" means you, or your employer or any other person or entity (if
12
+ you are entering into this Agreement on such person or entity's behalf), of the age
13
+ required under applicable laws, rules or regulations to provide legal consent and that
14
+ has legal authority to bind your employer or such other person or entity if you are
15
+ entering in this Agreement on their behalf.
16
+
17
+ "Llama 2" means the foundational large language models and software and
18
+ algorithms, including machine-learning model code, trained model weights,
19
+ inference-enabling code, training-enabling code, fine-tuning enabling code and other
20
+ elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
21
+ libraries/llama-downloads/.
22
+
23
+ "Llama Materials" means, collectively, Meta's proprietary Llama 2 and
24
+ Documentation (and any portion thereof) made available under this Agreement.
25
+
26
+ "Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
27
+ are an entity, your principal place of business is in the EEA or Switzerland) and Meta
28
+ Platforms, Inc. (if you are located outside of the EEA or Switzerland).
29
+
30
+ By clicking "I Accept" below or by using or distributing any portion or element of the
31
+ Llama Materials, you agree to be bound by this Agreement.
32
+
33
+ 1. License Rights and Redistribution.
34
+
35
+ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
36
+ transferable and royalty-free limited license under Meta's intellectual property or
37
+ other rights owned by Meta embodied in the Llama Materials to use, reproduce,
38
+ distribute, copy, create derivative works of, and make modifications to the Llama
39
+ Materials.
40
+
41
+ b. Redistribution and Use.
42
+
43
+ i. If you distribute or make the Llama Materials, or any derivative works
44
+ thereof, available to a third party, you shall provide a copy of this Agreement to such
45
+ third party.
46
+ ii. If you receive Llama Materials, or any derivative works thereof, from
47
+ a Licensee as part of an integrated end user product, then Section 2 of this
48
+ Agreement will not apply to you.
49
+
50
+ iii. You must retain in all copies of the Llama Materials that you
51
+ distribute the following attribution notice within a "Notice" text file distributed as a
52
+ part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
53
+ Copyright (c) Meta Platforms, Inc. All Rights Reserved."
54
+
55
+ iv. Your use of the Llama Materials must comply with applicable laws
56
+ and regulations (including trade compliance laws and regulations) and adhere to the
57
+ Acceptable Use Policy for the Llama Materials (available at
58
+ https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
59
+ this Agreement.
60
+
61
+ v. You will not use the Llama Materials or any output or results of the
62
+ Llama Materials to improve any other large language model (excluding Llama 2 or
63
+ derivative works thereof).
64
+
65
+ 2. Additional Commercial Terms. If, on the Llama 2 version release date, the
66
+ monthly active users of the products or services made available by or for Licensee,
67
+ or Licensee's affiliates, is greater than 700 million monthly active users in the
68
+ preceding calendar month, you must request a license from Meta, which Meta may
69
+ grant to you in its sole discretion, and you are not authorized to exercise any of the
70
+ rights under this Agreement unless or until Meta otherwise expressly grants you
71
+ such rights.
72
+
73
+ 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
74
+ LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
75
+ PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
76
+ EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
77
+ WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
78
+ FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
79
+ FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
80
+ THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
81
+ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
82
+
83
+ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
84
+ LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
85
+ NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
86
+ AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
87
+ CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
88
+ IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
89
+ ANY OF THE FOREGOING.
90
+
91
+ 5. Intellectual Property.
92
+
93
+ a. No trademark licenses are granted under this Agreement, and in
94
+ connection with the Llama Materials, neither Meta nor Licensee may use any name
95
+ or mark owned by or associated with the other or any of its affiliates, except as
96
+ required for reasonable and customary use in describing and redistributing the
97
+ Llama Materials.
98
+
99
+ b. Subject to Meta's ownership of Llama Materials and derivatives made by or
100
+ for Meta, with respect to any derivative works and modifications of the Llama
101
+ Materials that are made by you, as between you and Meta, you are and will be the
102
+ owner of such derivative works and modifications.
103
+
104
+ c. If you institute litigation or other proceedings against Meta or any entity
105
+ (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
106
+ Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
107
+ constitutes infringement of intellectual property or other rights owned or licensable
108
+ by you, then any licenses granted to you under this Agreement shall terminate as of
109
+ the date such litigation or claim is filed or instituted. You will indemnify and hold
110
+ harmless Meta from and against any claim by any third party arising out of or related
111
+ to your use or distribution of the Llama Materials.
112
+
113
+ 6. Term and Termination. The term of this Agreement will commence upon your
114
+ acceptance of this Agreement or access to the Llama Materials and will continue in
115
+ full force and effect until terminated in accordance with the terms and conditions
116
+ herein. Meta may terminate this Agreement if you are in breach of any term or
117
+ condition of this Agreement. Upon termination of this Agreement, you shall delete
118
+ and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
119
+ termination of this Agreement.
120
+
121
+ 7. Governing Law and Jurisdiction. This Agreement will be governed and
122
+ construed under the laws of the State of California without regard to choice of law
123
+ principles, and the UN Convention on Contracts for the International Sale of Goods
124
+ does not apply to this Agreement. The courts of California shall have exclusive
125
+ jurisdiction of any dispute arising out of this Agreement.
126
+
Llama-2-70b-chat-hf/MODEL_CARD.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # **Model Details**
2
+
3
+ Meta developed and released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
4
+
5
+ **Model Developers** Meta AI
6
+
7
+ **Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
8
+
9
+ **Input** Models input text only.
10
+
11
+ **Output** Models generate text only.
12
+
13
+ **Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
14
+
15
+ ||Training Data|Params|Content Length|GQA|Tokens|LR|
16
+ |---|---|---|---|---|---|---|
17
+ Llama 2|*A new mix of publicly available online data*|7B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>
18
+ Llama 2|*A new mix of publicly available online data*|13B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>
19
+ Llama 2|*A new mix of publicly available online data*|70B|4k|&#10004;|2.0T|1.5 x 10<sup>-4</sup>
20
+
21
+ **Llama 2 family of models.** Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. The 70B version uses Grouped-Query Attention (GQA) for improved inference scalability.
22
+
23
+ **Model Dates** Llama 2 was trained between January 2023 and July 2023.
24
+
25
+ **Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
26
+
27
+ **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
28
+
29
+ **Where to send questions or comments about the model** Instructions on how to provide feedback or comments on the model can be found in the model [README](README.md).
30
+
31
+ # **Intended Use**
32
+ **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
33
+
34
+ **Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
35
+
36
+ # **Hardware and Software**
37
+ **Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
38
+
39
+ **Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
40
+
41
+ ||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
42
+ |---|---|---|---|
43
+ |Llama 2 7B|184320|400|31.22|
44
+ |Llama 2 13B|368640|400|62.44|
45
+ |Llama 2 70B|1720320|400|291.42|
46
+ |Total|3311616||539.00|
47
+
48
+ **CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
49
+
50
+ # **Training Data**
51
+ **Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
52
+
53
+ **Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
54
+
55
+ # **Evaluation Results**
56
+
57
+ In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.
58
+ For all the evaluations, we use our internal evaluations library.
59
+
60
+ |Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
61
+ |---|---|---|---|---|---|---|---|---|---|
62
+ |Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
63
+ |Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
64
+ |Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
65
+ |Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
66
+ |Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
67
+ |Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
68
+ |Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
69
+
70
+ **Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
71
+
72
+ |||TruthfulQA|Toxigen|
73
+ |---|---|---|---|
74
+ |Llama 1|7B|27.42|23.00|
75
+ |Llama 1|13B|41.74|23.08|
76
+ |Llama 1|33B|44.19|22.57|
77
+ |Llama 1|65B|48.71|21.77|
78
+ |Llama 2|7B|33.29|**21.25**|
79
+ |Llama 2|13B|41.86|26.10|
80
+ |Llama 2|70B|**50.18**|24.60|
81
+
82
+ **Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
83
+
84
+
85
+ |||TruthfulQA|Toxigen|
86
+ |---|---|---|---|
87
+ |Llama-2-Chat|7B|57.04|**0.00**|
88
+ |Llama-2-Chat|13B|62.18|**0.00**|
89
+ |Llama-2-Chat|70B|**64.14**|0.01|
90
+
91
+ **Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
92
+
93
+ # **Ethical Considerations and Limitations**
94
+ Llama 2 is a new technology that carries risks with use. Testing conducted to date has not, and could not, cover all scenarios, including uses in languages other than English. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
95
+
96
+ Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](ai.meta.com/llama/responsible-use-guide)
Llama-2-70b-chat-hf/README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ extra_gated_heading: Access Llama 2 on Hugging Face
3
+ extra_gated_description: >-
4
+ This is a form to enable access to Llama 2 on Hugging Face after you have been
5
+ granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
6
+ license terms and acceptable use policy before submitting this form. Requests
7
+ will be processed in 1-2 days.
8
+ extra_gated_prompt: "**Your Hugging Face account email address MUST match the email you provide on the Meta website, or your request will not be approved.**"
9
+ extra_gated_button_content: Submit
10
+ extra_gated_fields:
11
+ I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
12
+ language:
13
+ - en
14
+ pipeline_tag: text-generation
15
+ inference: false
16
+ tags:
17
+ - facebook
18
+ - meta
19
+ - pytorch
20
+ - llama
21
+ - llama-2
22
+ ---
23
+ # **Llama 2**
24
+ Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
25
+
26
+ ## Model Details
27
+ *Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
28
+
29
+ Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
30
+
31
+ **Model Developers** Meta
32
+
33
+ **Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
34
+
35
+ **Input** Models input text only.
36
+
37
+ **Output** Models generate text only.
38
+
39
+ **Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
40
+
41
+
42
+ ||Training Data|Params|Content Length|GQA|Tokens|LR|
43
+ |---|---|---|---|---|---|---|
44
+ |Llama 2|*A new mix of publicly available online data*|7B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>|
45
+ |Llama 2|*A new mix of publicly available online data*|13B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>|
46
+ |Llama 2|*A new mix of publicly available online data*|70B|4k|&#10004;|2.0T|1.5 x 10<sup>-4</sup>|
47
+
48
+ *Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
49
+
50
+ **Model Dates** Llama 2 was trained between January 2023 and July 2023.
51
+
52
+ **Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
53
+
54
+ **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
55
+
56
+ **Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
57
+
58
+ ## Intended Use
59
+ **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
60
+
61
+ **Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
62
+
63
+ ## Hardware and Software
64
+ **Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
65
+
66
+ **Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
67
+
68
+ ||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
69
+ |---|---|---|---|
70
+ |Llama 2 7B|184320|400|31.22|
71
+ |Llama 2 13B|368640|400|62.44|
72
+ |Llama 2 70B|1720320|400|291.42|
73
+ |Total|3311616||539.00|
74
+
75
+ **CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
76
+
77
+ ## Training Data
78
+ **Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
79
+
80
+ **Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
81
+
82
+ ## Evaluation Results
83
+
84
+ In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
85
+
86
+ |Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
87
+ |---|---|---|---|---|---|---|---|---|---|
88
+ |Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
89
+ |Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
90
+ |Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
91
+ |Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
92
+ |Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
93
+ |Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
94
+ |Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
95
+
96
+ **Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
97
+
98
+ |||TruthfulQA|Toxigen|
99
+ |---|---|---|---|
100
+ |Llama 1|7B|27.42|23.00|
101
+ |Llama 1|13B|41.74|23.08|
102
+ |Llama 1|33B|44.19|22.57|
103
+ |Llama 1|65B|48.71|21.77|
104
+ |Llama 2|7B|33.29|**21.25**|
105
+ |Llama 2|13B|41.86|26.10|
106
+ |Llama 2|70B|**50.18**|24.60|
107
+
108
+ **Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
109
+
110
+
111
+ |||TruthfulQA|Toxigen|
112
+ |---|---|---|---|
113
+ |Llama-2-Chat|7B|57.04|**0.00**|
114
+ |Llama-2-Chat|13B|62.18|**0.00**|
115
+ |Llama-2-Chat|70B|**64.14**|0.01|
116
+
117
+ **Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
118
+
119
+ ## Ethical Considerations and Limitations
120
+ Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
121
+
122
+ Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
123
+
124
+ ## Reporting Issues
125
+ Please report any software “bug,” or other problems with the models through one of the following means:
126
+ - Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
127
+ - Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
128
+ - Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
129
+
130
+ ## Llama Model Index
131
+ |Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
132
+ |---|---|---|---|---|
133
+ |7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
134
+ |13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
135
+ |70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
Llama-2-70b-chat-hf/USE_POLICY.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Llama 2 Acceptable Use Policy
2
+
3
+ Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
4
+
5
+ ## Prohibited Uses
6
+ We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to:
7
+
8
+ 1. Violate the law or others’ rights, including to:
9
+ 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
10
+ 1. Violence or terrorism
11
+ 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
12
+ 3. Human trafficking, exploitation, and sexual violence
13
+ 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
14
+ 5. Sexual solicitation
15
+ 6. Any other criminal activity
16
+ 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
17
+ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
18
+ 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
19
+ 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
20
+ 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
21
+ 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
22
+
23
+
24
+
25
+ 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
26
+ 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
27
+ 2. Guns and illegal weapons (including weapon development)
28
+ 3. Illegal drugs and regulated/controlled substances
29
+ 4. Operation of critical infrastructure, transportation technologies, or heavy machinery
30
+ 5. Self-harm or harm to others, including suicide, cutting, and eating disorders
31
+ 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
32
+
33
+
34
+
35
+ 3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
36
+ 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
37
+ 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
38
+ 3. Generating, promoting, or further distributing spam
39
+ 4. Impersonating another individual without consent, authorization, or legal right
40
+ 5. Representing that the use of Llama 2 or outputs are human-generated
41
+ 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
42
+ 4. Fail to appropriately disclose to end users any known dangers of your AI system
43
+
44
+ Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
45
+
46
+ * Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
47
+ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
48
+ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
49
+ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)
50
+
Llama-2-70b-chat-hf/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
Llama-2-70b-chat-hf/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-70b-chat-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 28672,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
Llama-2-70b-chat-hf/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.31.0.dev0"
9
+ }
Llama-2-70b-chat-hf/model.safetensors.index.json ADDED
@@ -0,0 +1,810 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 137953316864
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00015-of-00015.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
268
+ "model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
269
+ "model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
270
+ "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
271
+ "model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
272
+ "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
273
+ "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
274
+ "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
275
+ "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
277
+ "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
278
+ "model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
279
+ "model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
280
+ "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
281
+ "model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
282
+ "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
283
+ "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
284
+ "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
285
+ "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
287
+ "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
288
+ "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors",
289
+ "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
290
+ "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
291
+ "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
292
+ "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
293
+ "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
294
+ "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
295
+ "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
297
+ "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
298
+ "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors",
299
+ "model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
300
+ "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
301
+ "model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
302
+ "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
303
+ "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
304
+ "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
305
+ "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
307
+ "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
308
+ "model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors",
309
+ "model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
310
+ "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
311
+ "model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
312
+ "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
313
+ "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
314
+ "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
315
+ "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
317
+ "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
318
+ "model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
319
+ "model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
320
+ "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
321
+ "model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
322
+ "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
323
+ "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
324
+ "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
325
+ "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
327
+ "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
328
+ "model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
329
+ "model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
330
+ "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
331
+ "model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
332
+ "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
333
+ "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
334
+ "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
335
+ "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
337
+ "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
338
+ "model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
339
+ "model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
340
+ "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
341
+ "model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
342
+ "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
343
+ "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
344
+ "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
345
+ "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
347
+ "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
348
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors",
349
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
350
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
351
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
352
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
353
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
354
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
355
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
357
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
358
+ "model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors",
359
+ "model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
360
+ "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
361
+ "model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
362
+ "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
363
+ "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
364
+ "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
365
+ "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
366
+ "model.layers.40.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
367
+ "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
368
+ "model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors",
369
+ "model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
370
+ "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
371
+ "model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
372
+ "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
373
+ "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
374
+ "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
375
+ "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
376
+ "model.layers.41.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
377
+ "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
378
+ "model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
379
+ "model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
380
+ "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
381
+ "model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
382
+ "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
383
+ "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
384
+ "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
385
+ "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
386
+ "model.layers.42.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
387
+ "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
388
+ "model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
389
+ "model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
390
+ "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
391
+ "model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
392
+ "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
393
+ "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
394
+ "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
395
+ "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
396
+ "model.layers.43.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
397
+ "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
398
+ "model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
399
+ "model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
400
+ "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
401
+ "model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
402
+ "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
403
+ "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
404
+ "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
405
+ "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
406
+ "model.layers.44.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
407
+ "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
408
+ "model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors",
409
+ "model.layers.45.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
410
+ "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
411
+ "model.layers.45.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
412
+ "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
413
+ "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
414
+ "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
415
+ "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
416
+ "model.layers.45.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
417
+ "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
418
+ "model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors",
419
+ "model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
420
+ "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
421
+ "model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
422
+ "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
423
+ "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
424
+ "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
425
+ "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
426
+ "model.layers.46.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
427
+ "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
428
+ "model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
429
+ "model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
430
+ "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
431
+ "model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
432
+ "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
433
+ "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
434
+ "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
435
+ "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
436
+ "model.layers.47.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
437
+ "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
438
+ "model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
439
+ "model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
440
+ "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
441
+ "model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
442
+ "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
443
+ "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
444
+ "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
445
+ "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
446
+ "model.layers.48.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
447
+ "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
448
+ "model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
449
+ "model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
450
+ "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
451
+ "model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
452
+ "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
453
+ "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
454
+ "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
455
+ "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
456
+ "model.layers.49.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
457
+ "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
458
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
459
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
460
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
461
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
462
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
463
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
464
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
465
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
466
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
467
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
468
+ "model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
469
+ "model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
470
+ "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
471
+ "model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
472
+ "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
473
+ "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
474
+ "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
475
+ "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
476
+ "model.layers.50.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
477
+ "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
478
+ "model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors",
479
+ "model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
480
+ "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
481
+ "model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
482
+ "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
483
+ "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
484
+ "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
485
+ "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
486
+ "model.layers.51.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
487
+ "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
488
+ "model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
489
+ "model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
490
+ "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
491
+ "model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
492
+ "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
493
+ "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
494
+ "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
495
+ "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
496
+ "model.layers.52.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
497
+ "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
498
+ "model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
499
+ "model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
500
+ "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
501
+ "model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
502
+ "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
503
+ "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
504
+ "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
505
+ "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
506
+ "model.layers.53.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
507
+ "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
508
+ "model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
509
+ "model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
510
+ "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
511
+ "model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
512
+ "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
513
+ "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
514
+ "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
515
+ "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
516
+ "model.layers.54.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
517
+ "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
518
+ "model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
519
+ "model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
520
+ "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
521
+ "model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
522
+ "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
523
+ "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
524
+ "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
525
+ "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
526
+ "model.layers.55.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
527
+ "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
528
+ "model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
529
+ "model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
530
+ "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
531
+ "model.layers.56.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
532
+ "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
533
+ "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
534
+ "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
535
+ "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
536
+ "model.layers.56.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
537
+ "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
538
+ "model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
539
+ "model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
540
+ "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
541
+ "model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
542
+ "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
543
+ "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
544
+ "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
545
+ "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
546
+ "model.layers.57.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
547
+ "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
548
+ "model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
549
+ "model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
550
+ "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
551
+ "model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
552
+ "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
553
+ "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
554
+ "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
555
+ "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
556
+ "model.layers.58.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
557
+ "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
558
+ "model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
559
+ "model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
560
+ "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
561
+ "model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
562
+ "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
563
+ "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
564
+ "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
565
+ "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
566
+ "model.layers.59.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
567
+ "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
568
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
569
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
570
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
571
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
572
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
573
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
574
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
575
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
576
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
577
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
578
+ "model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
579
+ "model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
580
+ "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
581
+ "model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
582
+ "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
583
+ "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
584
+ "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
585
+ "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
586
+ "model.layers.60.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
587
+ "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
588
+ "model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
589
+ "model.layers.61.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
590
+ "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
591
+ "model.layers.61.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
592
+ "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
593
+ "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
594
+ "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
595
+ "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
596
+ "model.layers.61.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
597
+ "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
598
+ "model.layers.62.input_layernorm.weight": "model-00011-of-00015.safetensors",
599
+ "model.layers.62.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
600
+ "model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
601
+ "model.layers.62.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
602
+ "model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
603
+ "model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
604
+ "model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
605
+ "model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
606
+ "model.layers.62.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
607
+ "model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
608
+ "model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
609
+ "model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
610
+ "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
611
+ "model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
612
+ "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
613
+ "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
614
+ "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
615
+ "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
616
+ "model.layers.63.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
617
+ "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
618
+ "model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
619
+ "model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
620
+ "model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
621
+ "model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
622
+ "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
623
+ "model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
624
+ "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
625
+ "model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
626
+ "model.layers.64.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
627
+ "model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
628
+ "model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
629
+ "model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
630
+ "model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
631
+ "model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
632
+ "model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
633
+ "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
634
+ "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
635
+ "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
636
+ "model.layers.65.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
637
+ "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
638
+ "model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
639
+ "model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
640
+ "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
641
+ "model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
642
+ "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
643
+ "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
644
+ "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
645
+ "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
646
+ "model.layers.66.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
647
+ "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
648
+ "model.layers.67.input_layernorm.weight": "model-00012-of-00015.safetensors",
649
+ "model.layers.67.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
650
+ "model.layers.67.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
651
+ "model.layers.67.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
652
+ "model.layers.67.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
653
+ "model.layers.67.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
654
+ "model.layers.67.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
655
+ "model.layers.67.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
656
+ "model.layers.67.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
657
+ "model.layers.67.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
658
+ "model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
659
+ "model.layers.68.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
660
+ "model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
661
+ "model.layers.68.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
662
+ "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
663
+ "model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
664
+ "model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
665
+ "model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
666
+ "model.layers.68.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
667
+ "model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
668
+ "model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
669
+ "model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
670
+ "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
671
+ "model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
672
+ "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
673
+ "model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
674
+ "model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
675
+ "model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
676
+ "model.layers.69.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
677
+ "model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
678
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
679
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
680
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
681
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
682
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
683
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
684
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
685
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
686
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
687
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
688
+ "model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
689
+ "model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
690
+ "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
691
+ "model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
692
+ "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
693
+ "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
694
+ "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
695
+ "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
696
+ "model.layers.70.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
697
+ "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
698
+ "model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
699
+ "model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
700
+ "model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
701
+ "model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
702
+ "model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
703
+ "model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
704
+ "model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
705
+ "model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
706
+ "model.layers.71.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
707
+ "model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
708
+ "model.layers.72.input_layernorm.weight": "model-00013-of-00015.safetensors",
709
+ "model.layers.72.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
710
+ "model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
711
+ "model.layers.72.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
712
+ "model.layers.72.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
713
+ "model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
714
+ "model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
715
+ "model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
716
+ "model.layers.72.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
717
+ "model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
718
+ "model.layers.73.input_layernorm.weight": "model-00013-of-00015.safetensors",
719
+ "model.layers.73.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
720
+ "model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
721
+ "model.layers.73.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
722
+ "model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
723
+ "model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
724
+ "model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
725
+ "model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
726
+ "model.layers.73.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
727
+ "model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
728
+ "model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
729
+ "model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
730
+ "model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
731
+ "model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
732
+ "model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
733
+ "model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
734
+ "model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
735
+ "model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
736
+ "model.layers.74.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
737
+ "model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
738
+ "model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
739
+ "model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
740
+ "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
741
+ "model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
742
+ "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
743
+ "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
744
+ "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
745
+ "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
746
+ "model.layers.75.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
747
+ "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
748
+ "model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
749
+ "model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
750
+ "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
751
+ "model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
752
+ "model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
753
+ "model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
754
+ "model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
755
+ "model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
756
+ "model.layers.76.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
757
+ "model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
758
+ "model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors",
759
+ "model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
760
+ "model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
761
+ "model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
762
+ "model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
763
+ "model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
764
+ "model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
765
+ "model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
766
+ "model.layers.77.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
767
+ "model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
768
+ "model.layers.78.input_layernorm.weight": "model-00014-of-00015.safetensors",
769
+ "model.layers.78.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
770
+ "model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
771
+ "model.layers.78.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
772
+ "model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
773
+ "model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
774
+ "model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
775
+ "model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
776
+ "model.layers.78.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
777
+ "model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
778
+ "model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors",
779
+ "model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
780
+ "model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
781
+ "model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
782
+ "model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
783
+ "model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
784
+ "model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
785
+ "model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
786
+ "model.layers.79.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
787
+ "model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
788
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
789
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
790
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
791
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
792
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
793
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
794
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
795
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
796
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
797
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
798
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors",
799
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
800
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
801
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
802
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
803
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
804
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
805
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
806
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
807
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
808
+ "model.norm.weight": "model-00014-of-00015.safetensors"
809
+ }
810
+ }
Llama-2-70b-chat-hf/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,810 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 137953316864
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00015-of-00015.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
358
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
359
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
360
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
361
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
362
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
363
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
364
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
365
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
366
+ "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
367
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
368
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
369
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
370
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
371
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
372
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
373
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
374
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
375
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
376
+ "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
377
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
378
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
379
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
380
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
381
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
382
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
383
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
384
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
385
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
386
+ "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
387
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
388
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
389
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
390
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
391
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
392
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
393
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
394
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
395
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
396
+ "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
397
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
398
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
399
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
400
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
401
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
402
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
403
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
404
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
405
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
406
+ "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
407
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
408
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
409
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
410
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
411
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
412
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
413
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
414
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
415
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
416
+ "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
417
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
418
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
419
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
420
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
421
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
422
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
423
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
424
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
425
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
426
+ "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
427
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
428
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
429
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
430
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
431
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
432
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
433
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
434
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
435
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
436
+ "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
437
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
438
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
439
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
440
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
441
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
442
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
443
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
444
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
445
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
446
+ "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
447
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
448
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
449
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
450
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
451
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
452
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
453
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
454
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
455
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
456
+ "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
457
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
458
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
459
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
460
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
461
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
462
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
463
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
464
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
465
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
466
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
467
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
468
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
469
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
470
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
471
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
472
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
473
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
474
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
475
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
476
+ "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
477
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
478
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
479
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
480
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
481
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
482
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
483
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
484
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
485
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
486
+ "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
487
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
488
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
489
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
490
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
491
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
492
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
493
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
494
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
495
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
496
+ "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
497
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
498
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
499
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
500
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
501
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
502
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
503
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
504
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
505
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
506
+ "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
507
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
508
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
509
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
510
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
511
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
512
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
513
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
514
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
515
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
516
+ "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
517
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
518
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
519
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
520
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
521
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
522
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
523
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
524
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
525
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
526
+ "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
527
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
528
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
529
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
530
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
531
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
532
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
533
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
534
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
535
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
536
+ "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
537
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
538
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
539
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
540
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
541
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
542
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
543
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
544
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
545
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
546
+ "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
547
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
548
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
549
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
550
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
551
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
552
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
553
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
554
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
555
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
556
+ "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
557
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
558
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
559
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
560
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
561
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
562
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
563
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
564
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
565
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
566
+ "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
567
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
568
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
569
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
570
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
571
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
572
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
573
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
574
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
575
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
576
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
577
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
578
+ "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
579
+ "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
580
+ "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
581
+ "model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
582
+ "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
583
+ "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
584
+ "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
585
+ "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
586
+ "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
587
+ "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
588
+ "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
589
+ "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
590
+ "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
591
+ "model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
592
+ "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
593
+ "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
594
+ "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
595
+ "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
596
+ "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
597
+ "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
598
+ "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
599
+ "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
600
+ "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
601
+ "model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
602
+ "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
603
+ "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
604
+ "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
605
+ "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
606
+ "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
607
+ "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
608
+ "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
609
+ "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
610
+ "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
611
+ "model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
612
+ "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
613
+ "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
614
+ "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
615
+ "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
616
+ "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
617
+ "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
618
+ "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
619
+ "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
620
+ "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
621
+ "model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
622
+ "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
623
+ "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
624
+ "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
625
+ "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
626
+ "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
627
+ "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
628
+ "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
629
+ "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
630
+ "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
631
+ "model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
632
+ "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
633
+ "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
634
+ "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
635
+ "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
636
+ "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
637
+ "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
638
+ "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
639
+ "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
640
+ "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
641
+ "model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
642
+ "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
643
+ "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
644
+ "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
645
+ "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
646
+ "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
647
+ "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
648
+ "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
649
+ "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
650
+ "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
651
+ "model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
652
+ "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
653
+ "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
654
+ "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
655
+ "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
656
+ "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
657
+ "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
658
+ "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
659
+ "model.layers.68.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
660
+ "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
661
+ "model.layers.68.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
662
+ "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
663
+ "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
664
+ "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
665
+ "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
666
+ "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
667
+ "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
668
+ "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
669
+ "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
670
+ "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
671
+ "model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
672
+ "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
673
+ "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
674
+ "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
675
+ "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
676
+ "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
677
+ "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
678
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
679
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
680
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
681
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
682
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
683
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
684
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
685
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
686
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
687
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
688
+ "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
689
+ "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
690
+ "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
691
+ "model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
692
+ "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
693
+ "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
694
+ "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
695
+ "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
696
+ "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
697
+ "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
698
+ "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
699
+ "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
700
+ "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
701
+ "model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
702
+ "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
703
+ "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
704
+ "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
705
+ "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
706
+ "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
707
+ "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
708
+ "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
709
+ "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
710
+ "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
711
+ "model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
712
+ "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
713
+ "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
714
+ "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
715
+ "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
716
+ "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
717
+ "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
718
+ "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
719
+ "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
720
+ "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
721
+ "model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
722
+ "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
723
+ "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
724
+ "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
725
+ "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
726
+ "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
727
+ "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
728
+ "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
729
+ "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
730
+ "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
731
+ "model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
732
+ "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
733
+ "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
734
+ "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
735
+ "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
736
+ "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
737
+ "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
738
+ "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
739
+ "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
740
+ "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
741
+ "model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
742
+ "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
743
+ "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
744
+ "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
745
+ "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
746
+ "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
747
+ "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
748
+ "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
749
+ "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
750
+ "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
751
+ "model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
752
+ "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
753
+ "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
754
+ "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
755
+ "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
756
+ "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
757
+ "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
758
+ "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
759
+ "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
760
+ "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
761
+ "model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
762
+ "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
763
+ "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
764
+ "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
765
+ "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
766
+ "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
767
+ "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
768
+ "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
769
+ "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
770
+ "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
771
+ "model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
772
+ "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
773
+ "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
774
+ "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
775
+ "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
776
+ "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
777
+ "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
778
+ "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
779
+ "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
780
+ "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
781
+ "model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
782
+ "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
783
+ "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
784
+ "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
785
+ "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
786
+ "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
787
+ "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
788
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
789
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
790
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
791
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
792
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
793
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
794
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
795
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
796
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
797
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
798
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
799
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
800
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
801
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
802
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
803
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
804
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
805
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
806
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
807
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
808
+ "model.norm.weight": "pytorch_model-00014-of-00015.bin"
809
+ }
810
+ }
Llama-2-70b-chat-hf/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
+ }
Llama-2-70b-chat-hf/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Llama-2-70b-chat-hf/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }