camenduru commited on
Commit
749195a
1 Parent(s): 97670a2

thanks to stabilityai ❤

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
LICENSE.txt ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ STABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT
2
+ Dated: July 27, 2023
3
+
4
+ "Agreement" means the terms and conditions for use, reproduction, distribution and modification of the Software Products set forth herein.
5
+
6
+ “Documentation” means any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software.
7
+
8
+ "Licensee" or "you" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity's behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
9
+
10
+ "Stability AI" or "we" means Stability AI Ltd.
11
+
12
+ "Software" means, collectively, Stability AI’s proprietary Stability Beluga 1 and 2 made available under this Agreement.
13
+
14
+ “Software Products” means Software and Documentation.
15
+
16
+ By using or distributing any portion or element of the Software Products, you agree to be bound by this Agreement.
17
+
18
+ License Rights and Redistribution.
19
+ Stability AI grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty free and limited license under Stability AI’s intellectual property or other rights owned by Stability AI embodied in the Software Products to reproduce, distribute, and create derivative works of the Software Products for purposes other than commercial or production use.
20
+ b. If you distribute or make the Software Products, or any derivative works thereof, available to a third party, you shall (i) provide a copy of this Agreement to such third party, and (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "Stability Beluga is licensed under the Stability Beluga Research License, Copyright (c) Stability AI Ltd. All Rights Reserved.”
21
+ c. The licenses granted to you under this Agreement are conditioned upon your compliance with the Documentation, this Agreement, and the Llama 2 Acceptable Use Policy available at ai.meta.com/llama/use-policy, which is hereby incorporated herein by reference, and whose restrictions will apply to both Llama 2 and the Software Products for purposes of this Agreement.
22
+ 2. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE SOFTWARE PRODUCTS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE SOFTWARE PRODUCTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE SOFTWARE PRODUCTS AND ANY OUTPUT AND RESULTS.
23
+ 3. Limitation of Liability. IN NO EVENT WILL STABILITY AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF STABILITY AI OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
24
+ 3. Intellectual Property.
25
+ a. No trademark licenses are granted under this Agreement, and in connection with the Software Products, neither Stability AI nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Software Products.
26
+ Subject to Stability AI’s ownership of the Software Products and derivatives made by or for Stability AI, with respect to any derivative works and modifications of the Software Products that are made by you, as between you and Stability AI, you are and will be the owner of such derivative works and modifications.
27
+ If you institute litigation or other proceedings against Stability AI (including a cross-claim or counterclaim in a lawsuit) alleging that the Software Products or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Stability AI from and against any claim by any third party arising out of or related to your use or distribution of the Software Products in violation of this Agreement.
28
+ 4. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Software Products and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Stability AI may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Software Products. Sections 2-4 shall survive the termination of this Agreement.
LLAMA 2 LICENSE/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 LICENSE/Responsible-Use-Guide.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525dc349d71fe257fce4098c146446df6fef4247174f351381e4c3214af126f0
3
+ size 1253223
LLAMA 2 LICENSE/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: [[email protected]](mailto:[email protected])
50
+
Notice ADDED
@@ -0,0 +1 @@
 
 
1
+ Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - conceptofmind/cot_submix_original
4
+ - conceptofmind/flan2021_submix_original
5
+ - conceptofmind/t0_submix_original
6
+ - conceptofmind/niv2_submix_original
7
+ language:
8
+ - en
9
+ pipeline_tag: text-generation
10
+ ---
11
+ # Stable Beluga 7B
12
+
13
+ ## Model Description
14
+
15
+ `Stable Beluga 7B` is a Llama2 7B model finetuned on an Orca style Dataset
16
+
17
+ ## Usage
18
+
19
+ Start chatting with `Stable Beluga 7B` using the following code snippet:
20
+
21
+ ```python
22
+ import torch
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
24
+
25
+ tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga-7B", use_fast=False)
26
+ model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga-7B", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
27
+ system_prompt = "### System:\nYou are StableBeluga, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
28
+
29
+ message = "Write me a poem please"
30
+ prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
31
+ inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
32
+ output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
33
+
34
+ print(tokenizer.decode(output[0], skip_special_tokens=True))
35
+ ```
36
+
37
+ Stable Beluga 7B should be used with this prompt format:
38
+ ```
39
+ ### System:
40
+ This is a system prompt, please behave and help the user.
41
+
42
+ ### User:
43
+ Your prompt here
44
+
45
+ ### Assistant:
46
+ The output of Stable Beluga 7B
47
+ ```
48
+
49
+ ## Model Details
50
+
51
+ * **Developed by**: [Stability AI](https://stability.ai/)
52
+ * **Model type**: Stable Beluga 7B is an auto-regressive language model fine-tuned on Llama2 7B.
53
+ * **Language(s)**: English
54
+ * **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
55
+ * **License**: Fine-tuned checkpoints (`Stable Beluga 7B`) is licensed under the [STABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT](https://huggingface.co/stabilityai/StableBeluga-7B/blob/main/LICENSE.txt)
56
+ * **Contact**: For questions and comments about the model, please email `[email protected]`
57
+
58
+ ### Training Dataset
59
+
60
+ ` Stable Beluga 7B` is trained on our internal Orca-style dataset
61
+
62
+ ### Training Procedure
63
+
64
+ Models are learned via supervised fine-tuning on the aforementioned datasets, trained in mixed-precision (BF16), and optimized with AdamW. We outline the following hyperparameters:
65
+
66
+ | Dataset | Batch Size | Learning Rate |Learning Rate Decay| Warm-up | Weight Decay | Betas |
67
+ |-------------------|------------|---------------|-------------------|---------|--------------|-------------|
68
+ | Orca pt1 packed | 256 | 3e-5 | Cosine to 3e-6 | 100 | 1e-6 | (0.9, 0.95) |
69
+ | Orca pt2 unpacked | 512 | 3e-5 | Cosine to 3e-6 | 100 | 1e-6 | (0.9, 0.95) |
70
+
71
+ ## Ethical Considerations and Limitations
72
+
73
+ Beluga 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, Beluga'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 Beluga, developers should perform safety testing and tuning tailored to their specific applications of the model.
74
+
75
+ ## Citations
76
+
77
+ ```bibtext
78
+ @misc{touvron2023llama,
79
+ title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
80
+ author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
81
+ year={2023},
82
+ eprint={2307.09288},
83
+ archivePrefix={arXiv},
84
+ primaryClass={cs.CL}
85
+ }
86
+ ```
87
+
88
+ ```bibtext
89
+ @misc{mukherjee2023orca,
90
+ title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
91
+ author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
92
+ year={2023},
93
+ eprint={2306.02707},
94
+ archivePrefix={arXiv},
95
+ primaryClass={cs.CL}
96
+ }
97
+ ```
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 11008,
11
+ "max_position_embeddings": 4096,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 32,
15
+ "num_key_value_heads": 32,
16
+ "pad_token_id": 0,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.32.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.32.0.dev0"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9b38b7ad2a95a0c8f7fa03595b62ba1d9739c7611e52b9c9b72291f7594c8b
3
+ size 9976578928
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef379abf2e0f2ef0a91f4c7a5ac3b8afb021bd0e846cbd8149c5eddb224644e
3
+ size 3500297344
model.safetensors.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
117
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
127
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
137
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
147
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
157
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
167
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
177
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
187
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
197
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
207
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
217
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
227
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
237
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
247
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
257
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
267
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
277
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
287
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
297
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
307
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
308
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
317
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
318
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
327
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.norm.weight": "model-00002-of-00002.safetensors"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 4096,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }