chrisjay pcuenq HF staff commited on
Commit
0a8e779
β€’
0 Parent(s):

Duplicate from huggingface-projects/llama-2-13b-chat

Browse files

Co-authored-by: Pedro Cuenca <[email protected]>

Files changed (8) hide show
  1. .gitattributes +35 -0
  2. LICENSE.txt +126 -0
  3. README.md +19 -0
  4. USE_POLICY.md +50 -0
  5. app.py +280 -0
  6. model.py +74 -0
  7. requirements.txt +8 -0
  8. style.css +16 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
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
+
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Llama 2 13b Chat
3
+ emoji: πŸ¦™
4
+ colorFrom: indigo
5
+ colorTo: pink
6
+ sdk: gradio
7
+ sdk_version: 3.37.0
8
+ app_file: app.py
9
+ pinned: false
10
+ license: other
11
+ suggested_hardware: a10g-small
12
+ duplicated_from: huggingface-projects/llama-2-13b-chat
13
+ ---
14
+
15
+ # LLAMA v2 Models
16
+
17
+ Llama v2 was introduced in [this paper](https://arxiv.org/abs/2307.09288).
18
+
19
+ This Space demonstrates [Llama-2-13b-chat-hf](meta-llama/Llama-2-13b-chat-hf) from Meta. Please, check the original model card for details.
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 (β€œPolicy”). 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 β€œbug,” 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
+
app.py ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from typing import Iterator
2
+
3
+ import gradio as gr
4
+ import torch
5
+
6
+ from model import get_input_token_length, run
7
+
8
+ DEFAULT_SYSTEM_PROMPT = """\
9
+ You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
10
+ """
11
+ MAX_MAX_NEW_TOKENS = 2048
12
+ DEFAULT_MAX_NEW_TOKENS = 1024
13
+ MAX_INPUT_TOKEN_LENGTH = 4000
14
+
15
+ DESCRIPTION = """
16
+ # Llama-2 13B Chat
17
+
18
+ This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
19
+
20
+ πŸ”Ž For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
21
+
22
+ πŸ”¨ Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
23
+ πŸ‡ For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
24
+
25
+ """
26
+
27
+ LICENSE = """
28
+ <p/>
29
+
30
+ ---
31
+ As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
32
+ this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
33
+ """
34
+
35
+ if not torch.cuda.is_available():
36
+ DESCRIPTION += '\n<p>Running on CPU πŸ₯Ά This demo does not work on CPU.</p>'
37
+
38
+
39
+ def clear_and_save_textbox(message: str) -> tuple[str, str]:
40
+ return '', message
41
+
42
+
43
+ def display_input(message: str,
44
+ history: list[tuple[str, str]]) -> list[tuple[str, str]]:
45
+ history.append((message, ''))
46
+ return history
47
+
48
+
49
+ def delete_prev_fn(
50
+ history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
51
+ try:
52
+ message, _ = history.pop()
53
+ except IndexError:
54
+ message = ''
55
+ return history, message or ''
56
+
57
+
58
+ def generate(
59
+ message: str,
60
+ history_with_input: list[tuple[str, str]],
61
+ system_prompt: str,
62
+ max_new_tokens: int,
63
+ temperature: float,
64
+ top_p: float,
65
+ top_k: int,
66
+ ) -> Iterator[list[tuple[str, str]]]:
67
+ if max_new_tokens > MAX_MAX_NEW_TOKENS:
68
+ raise ValueError
69
+
70
+ history = history_with_input[:-1]
71
+ generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
72
+ try:
73
+ first_response = next(generator)
74
+ yield history + [(message, first_response)]
75
+ except StopIteration:
76
+ yield history + [(message, '')]
77
+ for response in generator:
78
+ yield history + [(message, response)]
79
+
80
+
81
+ def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
82
+ generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
83
+ for x in generator:
84
+ pass
85
+ return '', x
86
+
87
+
88
+ def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
89
+ input_token_length = get_input_token_length(message, chat_history, system_prompt)
90
+ if input_token_length > MAX_INPUT_TOKEN_LENGTH:
91
+ raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')
92
+
93
+
94
+ with gr.Blocks(css='style.css') as demo:
95
+ gr.Markdown(DESCRIPTION)
96
+ gr.DuplicateButton(value='Duplicate Space for private use',
97
+ elem_id='duplicate-button')
98
+
99
+ with gr.Group():
100
+ chatbot = gr.Chatbot(label='Chatbot')
101
+ with gr.Row():
102
+ textbox = gr.Textbox(
103
+ container=False,
104
+ show_label=False,
105
+ placeholder='Type a message...',
106
+ scale=10,
107
+ )
108
+ submit_button = gr.Button('Submit',
109
+ variant='primary',
110
+ scale=1,
111
+ min_width=0)
112
+ with gr.Row():
113
+ retry_button = gr.Button('πŸ”„ Retry', variant='secondary')
114
+ undo_button = gr.Button('↩️ Undo', variant='secondary')
115
+ clear_button = gr.Button('πŸ—‘οΈ Clear', variant='secondary')
116
+
117
+ saved_input = gr.State()
118
+
119
+ with gr.Accordion(label='Advanced options', open=False):
120
+ system_prompt = gr.Textbox(label='System prompt',
121
+ value=DEFAULT_SYSTEM_PROMPT,
122
+ lines=6)
123
+ max_new_tokens = gr.Slider(
124
+ label='Max new tokens',
125
+ minimum=1,
126
+ maximum=MAX_MAX_NEW_TOKENS,
127
+ step=1,
128
+ value=DEFAULT_MAX_NEW_TOKENS,
129
+ )
130
+ temperature = gr.Slider(
131
+ label='Temperature',
132
+ minimum=0.1,
133
+ maximum=4.0,
134
+ step=0.1,
135
+ value=1.0,
136
+ )
137
+ top_p = gr.Slider(
138
+ label='Top-p (nucleus sampling)',
139
+ minimum=0.05,
140
+ maximum=1.0,
141
+ step=0.05,
142
+ value=0.95,
143
+ )
144
+ top_k = gr.Slider(
145
+ label='Top-k',
146
+ minimum=1,
147
+ maximum=1000,
148
+ step=1,
149
+ value=50,
150
+ )
151
+
152
+ gr.Examples(
153
+ examples=[
154
+ 'Hello there! How are you doing?',
155
+ 'Can you explain briefly to me what is the Python programming language?',
156
+ 'Explain the plot of Cinderella in a sentence.',
157
+ 'How many hours does it take a man to eat a Helicopter?',
158
+ "Write a 100-word article on 'Benefits of Open-Source in AI research'",
159
+ ],
160
+ inputs=textbox,
161
+ outputs=[textbox, chatbot],
162
+ fn=process_example,
163
+ cache_examples=True,
164
+ )
165
+
166
+ gr.Markdown(LICENSE)
167
+
168
+ textbox.submit(
169
+ fn=clear_and_save_textbox,
170
+ inputs=textbox,
171
+ outputs=[textbox, saved_input],
172
+ api_name=False,
173
+ queue=False,
174
+ ).then(
175
+ fn=display_input,
176
+ inputs=[saved_input, chatbot],
177
+ outputs=chatbot,
178
+ api_name=False,
179
+ queue=False,
180
+ ).then(
181
+ fn=check_input_token_length,
182
+ inputs=[saved_input, chatbot, system_prompt],
183
+ api_name=False,
184
+ queue=False,
185
+ ).success(
186
+ fn=generate,
187
+ inputs=[
188
+ saved_input,
189
+ chatbot,
190
+ system_prompt,
191
+ max_new_tokens,
192
+ temperature,
193
+ top_p,
194
+ top_k,
195
+ ],
196
+ outputs=chatbot,
197
+ api_name=False,
198
+ )
199
+
200
+ button_event_preprocess = submit_button.click(
201
+ fn=clear_and_save_textbox,
202
+ inputs=textbox,
203
+ outputs=[textbox, saved_input],
204
+ api_name=False,
205
+ queue=False,
206
+ ).then(
207
+ fn=display_input,
208
+ inputs=[saved_input, chatbot],
209
+ outputs=chatbot,
210
+ api_name=False,
211
+ queue=False,
212
+ ).then(
213
+ fn=check_input_token_length,
214
+ inputs=[saved_input, chatbot, system_prompt],
215
+ api_name=False,
216
+ queue=False,
217
+ ).success(
218
+ fn=generate,
219
+ inputs=[
220
+ saved_input,
221
+ chatbot,
222
+ system_prompt,
223
+ max_new_tokens,
224
+ temperature,
225
+ top_p,
226
+ top_k,
227
+ ],
228
+ outputs=chatbot,
229
+ api_name=False,
230
+ )
231
+
232
+ retry_button.click(
233
+ fn=delete_prev_fn,
234
+ inputs=chatbot,
235
+ outputs=[chatbot, saved_input],
236
+ api_name=False,
237
+ queue=False,
238
+ ).then(
239
+ fn=display_input,
240
+ inputs=[saved_input, chatbot],
241
+ outputs=chatbot,
242
+ api_name=False,
243
+ queue=False,
244
+ ).then(
245
+ fn=generate,
246
+ inputs=[
247
+ saved_input,
248
+ chatbot,
249
+ system_prompt,
250
+ max_new_tokens,
251
+ temperature,
252
+ top_p,
253
+ top_k,
254
+ ],
255
+ outputs=chatbot,
256
+ api_name=False,
257
+ )
258
+
259
+ undo_button.click(
260
+ fn=delete_prev_fn,
261
+ inputs=chatbot,
262
+ outputs=[chatbot, saved_input],
263
+ api_name=False,
264
+ queue=False,
265
+ ).then(
266
+ fn=lambda x: x,
267
+ inputs=[saved_input],
268
+ outputs=textbox,
269
+ api_name=False,
270
+ queue=False,
271
+ )
272
+
273
+ clear_button.click(
274
+ fn=lambda: ([], ''),
275
+ outputs=[chatbot, saved_input],
276
+ queue=False,
277
+ api_name=False,
278
+ )
279
+
280
+ demo.queue(max_size=20).launch()
model.py ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from threading import Thread
2
+ from typing import Iterator
3
+
4
+ import torch
5
+ from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
6
+
7
+ model_id = 'meta-llama/Llama-2-13b-chat-hf'
8
+
9
+ if torch.cuda.is_available():
10
+ config = AutoConfig.from_pretrained(model_id)
11
+ config.pretraining_tp = 1
12
+ model = AutoModelForCausalLM.from_pretrained(
13
+ model_id,
14
+ config=config,
15
+ torch_dtype=torch.float16,
16
+ load_in_4bit=True,
17
+ device_map='auto'
18
+ )
19
+ else:
20
+ model = None
21
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
22
+
23
+
24
+ def get_prompt(message: str, chat_history: list[tuple[str, str]],
25
+ system_prompt: str) -> str:
26
+ texts = [f'<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n']
27
+ # The first user input is _not_ stripped
28
+ do_strip = False
29
+ for user_input, response in chat_history:
30
+ user_input = user_input.strip() if do_strip else user_input
31
+ do_strip = True
32
+ texts.append(f'{user_input} [/INST] {response.strip()} </s><s>[INST] ')
33
+ message = message.strip() if do_strip else message
34
+ texts.append(f'{message} [/INST]')
35
+ return ''.join(texts)
36
+
37
+
38
+ def get_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> int:
39
+ prompt = get_prompt(message, chat_history, system_prompt)
40
+ input_ids = tokenizer([prompt], return_tensors='np', add_special_tokens=False)['input_ids']
41
+ return input_ids.shape[-1]
42
+
43
+
44
+ def run(message: str,
45
+ chat_history: list[tuple[str, str]],
46
+ system_prompt: str,
47
+ max_new_tokens: int = 1024,
48
+ temperature: float = 0.8,
49
+ top_p: float = 0.95,
50
+ top_k: int = 50) -> Iterator[str]:
51
+ prompt = get_prompt(message, chat_history, system_prompt)
52
+ inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda')
53
+
54
+ streamer = TextIteratorStreamer(tokenizer,
55
+ timeout=10.,
56
+ skip_prompt=True,
57
+ skip_special_tokens=True)
58
+ generate_kwargs = dict(
59
+ inputs,
60
+ streamer=streamer,
61
+ max_new_tokens=max_new_tokens,
62
+ do_sample=True,
63
+ top_p=top_p,
64
+ top_k=top_k,
65
+ temperature=temperature,
66
+ num_beams=1,
67
+ )
68
+ t = Thread(target=model.generate, kwargs=generate_kwargs)
69
+ t.start()
70
+
71
+ outputs = []
72
+ for text in streamer:
73
+ outputs.append(text)
74
+ yield ''.join(outputs)
requirements.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ accelerate==0.21.0
2
+ bitsandbytes==0.40.2
3
+ gradio==3.37.0
4
+ protobuf==3.20.3
5
+ scipy==1.11.1
6
+ sentencepiece==0.1.99
7
+ torch==2.0.1
8
+ transformers==4.31.0
style.css ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ h1 {
2
+ text-align: center;
3
+ }
4
+
5
+ #duplicate-button {
6
+ margin: auto;
7
+ color: white;
8
+ background: #1565c0;
9
+ border-radius: 100vh;
10
+ }
11
+
12
+ #component-0 {
13
+ max-width: 900px;
14
+ margin: auto;
15
+ padding-top: 1.5rem;
16
+ }