Update README.md
Browse files
README.md
CHANGED
@@ -1,199 +1,84 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
library_name: transformers
|
3 |
-
|
|
|
4 |
---
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
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]
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- ko
|
5 |
+
base_model:
|
6 |
+
- meta-llama/Llama-3.2-1B-Instruct
|
7 |
+
pipeline_tag: text-generation
|
8 |
library_name: transformers
|
9 |
+
datasets:
|
10 |
+
- nayohan/CodeFeedback-Filtered-Instruction-ko
|
11 |
---
|
12 |
+
- base_model : [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
|
13 |
+
- data_set : [nayohan/CodeFeedback-Filtered-Instruction-ko](https://huggingface.co/datasets/nayohan/CodeFeedback-Filtered-Instruction-ko)
|
14 |
+
- ํด๋น ๋ฐ์ดํฐ์
์ ์ ๋ถ ์ฌ์ฉํ๊ฑด ์๋๋ฉฐ Python์ธ์ด๋ฅผ ์ฐ์ ์ถ์ถํ๋ค์ ๋ฐ์ดํฐ์
๋ค์ ์๊น์๋ฅผ ํ์
, ๊ทธ ๋ค์ ์ ์ฒ๋ฆฌ๊ฐ ๊ณตํต์ ์ผ๋ก ๋ค์ด๊ฐ๋งํ ๋ฐ์ดํฐ๋ฅผ ๋ค์ ์ถ์ถํ์ฌ ํ์ต์ ์ฌ์ฉํ์ต๋๋ค.
|
15 |
+
- ์ด ํ์ต ๋ฐ์ดํฐ ๊ฑด : 49,859 ๊ฑด
|
16 |
+
|
17 |
+
```python
|
18 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
19 |
+
|
20 |
+
model_id = 'MDDDDR/llama3.2-1B-Instruct-FFT-code-python'
|
21 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
22 |
+
model = AutoModelForCausalLM.from_pretrained(model_id,
|
23 |
+
device_map="cuda:0",
|
24 |
+
torch_dtype=torch.bfloat16)
|
25 |
+
|
26 |
+
|
27 |
+
instruction = '''LCS(Longest Common Subsequence, ์ต์ฅ ๊ณตํต ๋ถ๋ถ ์์ด)๋ฌธ์ ๋ ๋ ์์ด์ด ์ฃผ์ด์ก์ ๋, ๋ชจ๋์ ๋ถ๋ถ ์์ด์ด ๋๋ ์์ด ์ค ๊ฐ์ฅ ๊ธด ๊ฒ์ ์ฐพ๋ ๋ฌธ์ ์ด๋ค.
|
28 |
+
|
29 |
+
์๋ฅผ ๋ค์ด, ACAYKP์ CAPCAK์ LCS๋ ACAK๊ฐ ๋๋ค.
|
30 |
+
|
31 |
+
###์
๋ ฅ : ์ฒซ์งธ ์ค๊ณผ ๋์งธ ์ค์ ๋ ๋ฌธ์์ด์ด ์ฃผ์ด์ง๋ค. ๋ฌธ์์ด์ ์ํ๋ฒณ ๋๋ฌธ์๋ก๋ง ์ด๋ฃจ์ด์ ธ ์์ผ๋ฉฐ, ์ต๋ 1000๊ธ์๋ก ์ด๋ฃจ์ด์ ธ ์๋ค.
|
32 |
+
###์ถ๋ ฅ : ์ฒซ์งธ ์ค์ ์
๋ ฅ์ผ๋ก ์ฃผ์ด์ง ๋ ๋ฌธ์์ด์ LCS์ ๊ธธ์ด๋ฅผ ์ถ๋ ฅํ๋ค.
|
33 |
+
|
34 |
+
###์
๋ ฅ ์์ :
|
35 |
+
ACAYKP
|
36 |
+
CAPCAK
|
37 |
+
###์ถ๋ ฅ ์์ : 4
|
38 |
+
'''
|
39 |
+
|
40 |
+
messages = [
|
41 |
+
{
|
42 |
+
"role":"user",
|
43 |
+
"content":"์๋๋ ๋ฌธ์ ๋ฅผ ์ค๋ช
ํ๋ ์ง์์ฌํญ์
๋๋ค. ์ด ์์ฒญ์ ๋ํด ์ ์ ํ๊ฒ ๋ต๋ณํด์ฃผ์ธ์.\n###์ง์์ฌํญ:{instruction}\n###๋ต๋ณ:".format(instruction=instruction)
|
44 |
+
}
|
45 |
+
]
|
46 |
+
|
47 |
+
with torch.no_grad():
|
48 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
|
49 |
+
inputs = tokenizer(prompt, return_tensors="pt", padding=False).to('cuda')
|
50 |
+
outputs = model.generate(**inputs,
|
51 |
+
use_cache=False,
|
52 |
+
max_length=256,
|
53 |
+
top_p=0.9,
|
54 |
+
temperature=0.7,
|
55 |
+
repetition_penalty=1.0,
|
56 |
+
pad_token_id=tokenizer.pad_token_id)
|
57 |
+
|
58 |
+
output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
59 |
+
final_output = output_text.split('assistant')[-1].strip()
|
60 |
+
print(final_output)
|
61 |
+
# ###๋ต๋ณ:```python
|
62 |
+
# def longest_common_subsequence(str1, str2):
|
63 |
+
# m = len(str1)
|
64 |
+
# n = len(str2)
|
65 |
+
# dp = [[0] * (n+1) for _ in range(m+1)]
|
66 |
+
#
|
67 |
+
# for i in range(m+1):
|
68 |
+
# for j in range(n+1):
|
69 |
+
# if i == 0 or j == 0:
|
70 |
+
# dp[i][j] = 0
|
71 |
+
# elif str1[i-1] == str2[j-1]:
|
72 |
+
# dp[i][j] = dp[i-1][j-1] + 1
|
73 |
+
# else:
|
74 |
+
# dp[i][j] = max(dp[i-1][j], dp[i][j-1])
|
75 |
+
#
|
76 |
+
# return dp[m][n]
|
77 |
+
#
|
78 |
+
# print(longest_common_subsequence("ACAYKP", "CAPCAK")) # Output: 4
|
79 |
+
```
|
80 |
+
```
|
81 |
+
|
82 |
+
Hardware
|
83 |
+
- A100 40GB x 1
|
84 |
+
- Training Time : 1 hour 45 minutes
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|