QuantumIntelligence commited on
Commit
f3fb870
โ€ข
1 Parent(s): e924c46

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -161
README.md CHANGED
@@ -1,201 +1,132 @@
1
  ---
 
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
9
 
 
10
 
11
 
12
- ## Model Details
13
 
14
- ### Model Description
15
 
16
- <!-- Provide a longer summary of what this model is. -->
 
 
 
17
 
18
- This is the model card of a ๐Ÿค— transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
 
28
- ### Model Sources [optional]
 
 
29
 
30
- <!-- Provide the basic links for the model. -->
 
 
 
 
 
 
31
 
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
 
35
 
36
- ## Uses
 
 
37
 
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
 
40
- ### Direct Use
 
 
 
 
 
 
41
 
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
 
43
 
44
- [More Information Needed]
 
45
 
46
- ### Downstream Use [optional]
 
 
 
 
 
 
 
 
47
 
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
 
49
 
50
- [More Information Needed]
 
51
 
52
- ### Out-of-Scope Use
53
 
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
 
56
- [More Information Needed]
 
 
 
 
 
 
57
 
58
- ## Bias, Risks, and Limitations
 
 
59
 
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
 
62
- [More Information Needed]
 
63
 
64
- ### Recommendations
 
 
65
 
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
67
 
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
- ## How to Get Started with the Model
71
 
72
- Use the code below to get started with the model.
 
 
73
 
74
- [More Information Needed]
 
75
 
76
- ## Training Details
77
 
78
- ### Training Data
79
 
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
200
 
 
 
201
 
 
 
1
  ---
2
+ license: apache-2.0
3
  library_name: transformers
4
+ tags:
5
+ - Korean
6
+ - LLM
7
+ - Chatbot
8
+ - DPO
9
+ - Intel/neural-chat-7b-v3-3
10
  ---
11
 
12
+ # QI-neural-chat-7B-ko-DPO
13
 
14
+ This is a fine tuned model based on the [neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3) with Korean DPO dataset([Oraca-DPO-Pairs-KO](https://huggingface.co/datasets/Ja-ck/Orca-DPO-Pairs-KO)).
15
 
16
+ It processes Korean language relatively well, so it is useful when creating various applications.
17
 
18
 
 
19
 
20
+ ### Basic Usage
21
 
22
+ ```
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
24
+ import transformers
25
+ import torch
26
 
 
27
 
28
+ model_id = "QuantumIntelligence/QI-neural-chat-7B-ko-DPO"
 
 
 
 
 
 
29
 
30
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
31
+ # model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
32
+ model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True) # quantization
33
 
34
+ pipeline = transformers.pipeline(
35
+ "text-generation",
36
+ model=model,
37
+ torch_dtype=torch.float16,
38
+ device_map="auto",
39
+ tokenizer=tokenizer,
40
+ )
41
 
42
+ prompt = """Classify the text into neutral, negative or positive.
43
+ Text: This movie is definitely one of my favorite movies of its kind. The interaction between respectable and morally strong characters is an ode to chivalry and the honor code amongst thieves and policemen.
44
+ Sentiment:
45
+ """
46
 
47
+ outputs = pipeline(prompt, max_new_tokens=6)
48
+ print(outputs[0]["generated_text"])
49
+ ```
50
 
51
+ ### Using Korean
52
 
53
+ - Sentiment
54
+ ```
55
+ prompt = """
56
+ ๋‹ค์Œ ํ…์ŠคํŠธ๋ฅผ ์ค‘๋ฆฝ, ๋ถ€์ •, ๊ธ์ •์œผ๋กœ ๋ถ„๋ฅ˜ํ•ด์ค˜.
57
+ ํ…์ŠคํŠธ: ํ•˜๋Š˜์„ ๋ณด๋‹ˆ ๋น„๊ฐ€ ์˜ฌ๋“ฏ ํ•˜๋‹ค. ์šฐ์šธํ•œ ๊ธฐ๋ถ„์ด ๋“ค์–ด์„œ ์ˆ ์„ ํ•œ์ž” ํ• ๊นŒ ๊ณ ๋ฏผ์ค‘์ธ๋ฐ ๊ฐ™์ด ๋งˆ์‹ค ์‚ฌ๋žŒ์ด ์—†๋‹ค.
58
+ ๋ถ„๋ฅ˜:
59
+ """
60
 
61
+ outputs = pipeline(prompt, max_new_tokens=6)
62
+ print(outputs[0]["generated_text"])
63
+ ```
64
 
65
+ - Summarization
66
+ ```
67
 
68
+ prompt = """
69
+ ๊ตญ๋‚ด ์—ฐ๊ตฌ์ง„์ด ๋ฏธ๊ตญ, ์˜๊ตญ ๊ณต๋™ ์—ฐ๊ตฌํŒ€๊ณผ ์ฒญ๊ฐ ๊ธฐ๋Šฅ์— ๊ด€์—ฌํ•˜๋Š” ๋‹จ๋ฐฑ์งˆ ๊ตฌ์กฐ๋ฅผ ๊ทœ๋ช…ํ–ˆ๋‹ค. ๋‚œ์ฒญ ์น˜๋ฃŒ๋ฒ•์„ ๊ฐœ๋ฐœํ•˜๋Š” ๋ฐ ๋„์›€์ด ๋  ๊ฒƒ์œผ๋กœ ๋ณด์ธ๋‹ค.
70
+ ํฌ์Šคํ…์€ ์กฐ์œค์ œ ์ƒ๋ช…๊ณผํ•™๊ณผ ๊ต์ˆ˜ ์—ฐ๊ตฌํŒ€์ด ๊น€๊ด‘ํ‘œ ๊ฒฝํฌ๋Œ€ ์‘์šฉํ™”ํ•™๊ณผ ๊ต์ˆ˜ ์—ฐ๊ตฌํŒ€, ๋ธŒ์…ฐ๋ณผ๋กœ๋“œ ์นดํŠธ๋ฆฌ์น˜ ๋ฏธ๊ตญ ์„œ๋˜ ์บ˜๋ฆฌํฌ๋‹ˆ์•„๋Œ€ ๊ต์ˆ˜ ์—ฐ๊ตฌํŒ€, ์บ๋กค ๋กœ๋นˆ์Šจ ์˜๊ตญ ์˜ฅ์Šคํผ๋“œ๋Œ€ ๊ต์ˆ˜์™€ ํ•จ๊ป˜ ์ฒญ๊ฐ ๊ด€๋ จ ํŠน์ • ์ˆ˜์šฉ์ฒด ๋‹จ๋ฐฑ์งˆ ๊ตฌ์กฐ์™€ ๋ฉ”์ปค๋‹ˆ์ฆ˜์„ ๋ฐํžˆ๋Š” ๋ฐ ์„ฑ๊ณตํ–ˆ๋‹ค๊ณ  11์ผ ๋ฐํ˜”๋‹ค.
71
+ ๊ท€ ์•ˆ์ชฝ์—๋Š” ์†Œ๋ฆฌ๋ฅผ ๊ฐ์ง€ํ•˜๋Š” ๋‹ฌํŒฝ์ด๊ด€๊ณผ ํ‰ํ˜•๊ฐ๊ฐ์„ ๋‹ด๋‹นํ•˜๋Š” ์ „์ •๊ธฐ๊ด€์ด ์žˆ๋‹ค. ์ด ๊ธฐ๊ด€๋“ค์˜ ์„ธํฌ๋“ค์€ ์ˆ˜์šฉ์ฒด ๋‹จ๋ฐฑ์งˆ์ธ โ€˜GPR156โ€™์„ ๊ฐ–๊ณ  ์žˆ๋‹ค. GPR156์ด ํ™œ์„ฑํ™”๋˜๋ฉด ์„ธํฌ ๋‚ด G๋‹จ๋ฐฑ์งˆ๊ณผ ๊ฒฐํ•ฉํ•ด ์‹ ํ˜ธ๋ฅผ ์ „๋‹ฌํ•œ๋‹ค. G๋‹จ๋ฐฑ์งˆ์€ โ€˜๊ตฌ์•„๋‹Œ ๋‰ดํด๋ ˆ์˜คํƒ€์ด๋“œ-๊ฒฐํ•ฉ ๋‹จ๋ฐฑ์งˆโ€™๋กœ ์‹ ํ˜ธ๋ฅผ ์ „๋‹ฌํ•˜๋Š” ์ค‘๊ฐœ์ž๋‹ค.
72
+ GPR156์€ ๋‹ค๋ฅธ ์ˆ˜์šฉ์ฒด์™€ ๋‹ฌ๋ฆฌ ํŠน๋ณ„ํ•œ ์ž๊ทน์ด ์—†์–ด๋„ ํ•ญ์ƒ ๋†’์€ ํ™œ์„ฑ์„ ์œ ์ง€ํ•˜๋ฉฐ ์ฒญ๊ฐ๊ณผ ํ‰ํ˜• ๊ธฐ๋Šฅ ์œ ์ง€์— ํฐ ์—ญํ• ์„ ํ•œ๋‹ค. ์„ ์ฒœ์ ์œผ๋กœ ์ฒญ๊ฐ ์žฅ์• ๊ฐ€ ์žˆ๋Š” ํ™˜์ž๋“ค์„ ์น˜๋ฃŒํ•˜๊ธฐ ์œ„ํ•ด์„œ๋Š” ์ด ๋‹จ๋ฐฑ์งˆ์˜ ๊ตฌ์กฐ์™€ ์ž‘์šฉ ๋ฉ”์ปค๋‹ˆ์ฆ˜์„ ์•Œ์•„์•ผ ํ•œ๋‹ค.
73
+ ์—ฐ๊ตฌํŒ€์€ ์ดˆ์ €์˜จ์ „์žํ˜„๋ฏธ๊ฒฝ(Cryo-EM) ๋ถ„์„๋ฒ•์„ ์‚ฌ์šฉํ•ด GPR156๊ณผ GPR156-G๋‹จ๋ฐฑ์งˆ ๊ฒฐํ•ฉ ๋ณตํ•ฉ์ฒด๋ฅผ ๊ณ ํ•ด์ƒ๋„๋กœ ๊ด€์ฐฐํ–ˆ๋‹ค. ์ด๋ฅผ ํ†ตํ•ด ์ˆ˜์šฉ์ฒด๋ฅผ ํ™œ์„ฑํ™”ํ•˜๋Š” ์ž‘์šฉ์ œ ์—†์ด๋„ GPR156์ด ๋†’์€ ํ™œ์„ฑ์„ ์œ ์ง€ํ•  ์ˆ˜ ์žˆ๋Š” ์›์ธ์„ ์ฐพ์•˜๋‹ค.
74
+ GPR156์€ ์„ธํฌ๋ง‰์— ํ’๋ถ€ํ•œ ์ธ์ง€์งˆ๊ณผ ๊ฒฐํ•ฉํ•ด ํ™œ์„ฑํ™”๋๋‹ค. ์„ธํฌ์งˆ์— ์žˆ๋Š” G๋‹จ๋ฐฑ์งˆ๊ณผ์˜ ์ƒํ˜ธ์ž‘์šฉ์„ ํ†ตํ•ด ์ž์ฒด์ ์œผ๋กœ ๊ตฌ์กฐ๋ฅผ ๋ณ€ํ˜•, ๋†’์€ ํ™œ์„ฑ์„ ์œ ์ง€ํ•œ๋‹ค๋Š” ์‚ฌ์‹ค๋„ ํ™•์ธ๋๋‹ค.
75
+ ๊ธฐ์กด์— ์•Œ๋ ค์ง„ ์ˆ˜์šฉ์ฒด ๋‹จ๋ฐฑ์งˆ๋“ค๊ณผ ๋‹ฌ๋ฆฌ GPR156์€ ์„ธํฌ๋ง‰์„ ํ†ต๊ณผํ•˜๋Š” 7๋ฒˆ์งธ ํž๋ฆญ์Šค ๋ง๋‹จ ๋ถ€๋ถ„์˜ ๊ตฌ์กฐ๋ฅผ ์œ ์—ฐํ•˜๊ฒŒ ๋ฐ”๊พธ๋ฉฐ G๋‹จ๋ฐฑ์งˆ๊ณผ์˜ ๊ฒฐํ•ฉ์„ ์œ ๋„ํ–ˆ๏ฟฝ๏ฟฝ. ์ด๋ฅผ ํ†ตํ•ด ์‹ ํ˜ธ๋ฅผ ํ™œ์„ฑํ™”ํ•จ์œผ๋กœ์จ ์†Œ๋ฆฌ๋ฅผ ๊ฐ์ง€ํ•˜๋Š” ๋ฐ ๋„์›€์„ ์ฃผ์—ˆ๋‹ค.
76
+ ์กฐ ๊ต์ˆ˜๋Š” โ€œ์„ ์ฒœ์ ์œผ๋กœ ๋‚œ์ฒญ๊ณผ ๊ท ํ˜• ๊ฐ๊ฐ ๊ธฐ๋Šฅ์— ์žฅ์• ๊ฐ€ ์žˆ๋Š” ํ™˜์ž๋“ค์ด ๋งŽ๋‹คโ€๋ฉฐ โ€œ์ด๋“ค์„ ์œ„ํ•œ ํš๊ธฐ์ ์ธ ์น˜๋ฃŒ๋ฒ•๊ณผ ์•ฝ๋ฌผ ๊ฐœ๋ฐœ์— ์ด๋ฒˆ ์—ฐ๊ตฌ๊ฐ€ ํฐ ๋„์›€์ด ๋˜๊ธธ ๋ฐ”๋ž€๋‹คโ€๊ณ  ๋งํ–ˆ๋‹ค. ์—ฐ๊ตฌ ๋…ผ๋ฌธ์€ ๊ตญ์ œํ•™์ˆ ์ง€ โ€˜๋„ค์ด์ฒ˜ ๊ตฌ์กฐ&๋ถ„์ž ์ƒ๋ฌผํ•™โ€™ ์˜จ๋ผ์ธํŒ์— ์ตœ๊ทผ ๊ฒŒ์žฌ๋๋‹ค.
77
 
78
+ ์œ„ ๋ฌธ์žฅ์„ ํ•œ๊ธ€๋กœ 100์ž๋‚ด๋กœ ์š”์•ฝํ•ด์ค˜.
79
+ ์š”์•ฝ:
80
+ """
81
 
82
+ outputs = pipeline(prompt, max_new_tokens=256, return_full_text = False, pad_token_id=tokenizer.eos_token_id)&&
83
+ print(outputs[0]["generated_text"])
84
 
 
85
 
86
+ ```
87
 
88
+ - Question answering
89
+ ```
90
+ prompt = """
91
+ ์ฐธ๊ฐ€์ž๋“ค์€ ๋จผ์ € fMRI ๊ธฐ๊ธฐ ์•ˆ์—์„œ ์ž์‹ ์˜ ์ด์•ผ๊ธฐ๋ฅผ ์ฝ๋Š” ๋™์•ˆ ๋‡Œ์˜ ํ™œ๋™ ํŒจํ„ด์„ ๊ธฐ๋กํ–ˆ๋‹ค. ์ด์•ผ๊ธฐ๋ฅผ ๋‹ค์‹œ ์ฝ์œผ๋ฉด์„œ๋Š” ์ด์•ผ๊ธฐ ์† ๋‹จ์–ด์— ๋Œ€ํ•ด ์ˆœ๊ฐ„์ˆœ๊ฐ„ ์ž์‹ ์ด ๋Š๋ผ๋Š” ์ž๊ธฐ ๊ด€๋ จ๋„, ๊ธยท๋ถ€์ • ์ •์„œ๋ฅผ ๋ณด๊ณ ํ–ˆ๋‹ค. ์ˆ˜์ง‘๋œ 49๋ช…์˜ ๋ฐ์ดํ„ฐ๋Š” ์ž๊ธฐ ๊ด€๋ จ๋„์™€ ๊ธยท๋ถ€์ • ์ •์„œ ์ ์ˆ˜์— ๋”ฐ๋ผ ๋‹ค์„ฏ ๊ฐœ ์ˆ˜์ค€์œผ๋กœ ๋ถ„๋ฅ˜๋๋‹ค.
92
+ ์งˆ๋ฌธ: ์‹คํ—˜์˜ ๋Œ€์ƒ์ด ๋œ ์‚ฌ๋žŒ์€ ๋ช‡ ๋ช…์ธ๊ฐ€? ํ•œ๊ธ€๋กœ ๋Œ€๋‹ต.
93
+ ๋Œ€๋‹ต:
94
+ """
95
 
96
+ outputs = pipeline(prompt, max_new_tokens=30, return_full_text = False)
97
+ generated_text = outputs[0]["generated_text"]
98
+ print(generated_text)
99
 
100
+ ```
101
 
102
+ - Reasoning
103
+ ```
104
 
105
+ prompt = """
106
+ ๊ฐ ๋ฐฉ์— ๊ณต์ด 5๊ฐœ ์žˆ๊ณ , ๋ฐฉ์˜ ์ด ๊ฐœ์ˆ˜๋Š” 4. ์ด ๊ณต์˜ ๊ฐฏ์ˆ˜๋Š” ๋ช‡๊ฐœ ์ธ๊ฐ€?
107
+ """
108
 
109
+ outputs = pipeline(prompt, max_new_tokens=40, return_full_text = False, pad_token_id=tokenizer.eos_token_id)
110
+ print(outputs[0]["generated_text"])
111
 
112
+ ```
113
 
114
+ - Chatbot template
115
 
116
+ ```
117
+ messages = [{"role": "user", "content": "์ข‹์€ ์ทจ๋ฏธ๋ฅผ ๊ฐ€์ง€๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•˜๋‚˜์š”?"}]
118
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
119
 
120
+ outputs = pipeline(prompt, max_new_tokens=512, do_sample=True, temperature=0.7, top_k=50, top_p=0.95, return_full_text = False)
121
+ generated_text = outputs[0]["generated_text"]
122
 
123
+ print(generated_text)
124
 
125
+ ```
126
 
127
+ ### Request
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
128
 
129
+ The support of GPU computing resource is required for the development and implementation of state-of-the-art models.
130
+ I would appreciate if anyone could help.
131
 
132