File size: 4,295 Bytes
a9649b9 e4e0301 311dd65 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 a9649b9 e4e0301 |
1 2 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 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
# VietCoMath Model Usage
## Overview
This example snipe code for running the VietCoMath-01 small model for mathematical Coding problem-solving and General Multi tasks.
This model is based from LLama 3.0 8B.
#### Helper Functions
```python
import re
def check_patterns(response):
"""
Check if the response contains all required XML patterns.
Args:
response (str): The model's generated response
Returns:
str: Parsed response or 'Missing' if patterns are incomplete
"""
patterns = {
'answer': r'<answer>(.*?)</answer>',
'reflection': r'<reflection>(.*?)</reflection>',
'steps': r'<step>(.*?)</step>',
'count': r'<count>(.*?)</count>'
}
matches = {
'answer': re.search(patterns['answer'], response, re.DOTALL),
'reflection': re.search(patterns['reflection'], response, re.DOTALL),
'steps': re.findall(patterns['steps'], response, re.DOTALL),
'count': re.findall(patterns['count'], response, re.DOTALL)
}
return "Missing" if not all([matches['answer'], matches['reflection'], matches['steps'], matches['count']]) else response
def parse_response(response):
"""
Parse the model's response and extract key components.
Args:
response (str): The model's generated response
Returns:
tuple: Parsed answer, reflection, steps, and clarification
"""
response_check = check_patterns(response)
if response_check == "Missing":
clarification_match = re.search(r'<clarification>(.*?)</clarification>', response, re.DOTALL)
clarification = clarification_match.group(1).strip() if clarification_match else response
return "", "", [], clarification
else:
answer_match = re.search(r'<answer>(.*?)</answer>', response, re.DOTALL)
reflection_match = re.search(r'<reflection>(.*?)</reflection>', response, re.DOTALL)
answer = answer_match.group(1).strip() if answer_match else ""
reflection = reflection_match.group(1).strip() if reflection_match else ""
steps = re.findall(r'<step>(.*?)</step>', response, re.DOTALL)
return answer, reflection, steps, ""
```
## Usage
### Basic Text Generation
```python
import transformers
import torch
# Load the model
model_id = "VietnamAIHub/VietCoMath-o1-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
# Example mathematical word problem
problem = "Có 100 sinh viên đỗ đại học. Trong số đó, có 55 sinh viên chọn âm nhạc, 44 sinh viên chọn thể thao, và 20 sinh viên chọn cả 2. Hỏi có bao nhiêu sinh viên không chọn âm nhạc, cũng không chọn thể thao?"
# Prepare messages
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": f"{problem}"},
]
# Define terminators
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
# Generate text
outputs = pipeline(
messages,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
# Print generated text
generated_text=outputs[0]["generated_text"][-1]
answer, reflection, steps, clarification = parse_response(generated_text)
print(clarification)
print("------------Internal Thinking-------------")
print(steps)
print(reflection)
print("------------End of Internal Thinking-------------\n")
print("------------Final Answer-------------")
print(answer)
print("------------End of Answer-------------")
## Limitations
- The model is Small scale May Failed in Very difficult problems, Please check the result
## License
[Model is based LLama 3B]
## Citation
@misc {VietnamAIHub,
author = { {VietnamAIHub} },
title = { VietCoMath-o1-8B},
year = 2024,
url = { https://huggingface.co/VietnamAIHub/VietCoMath-o1-8B },
doi = { 10.57967/hf/3743 },
publisher = { Hugging Face }
}
## Collaboration & Contribution
Bạn có thể kết nối trực tiếp với Trần Nhiệm [email protected]
Hoặc có thể chat trực tiếp ở: LinkedIn Facebook. X. Zalo +886 934 311 751
|