利用混合质量数据提升开源语言模型

from openmind import pipeline, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
from torch import Tensor
import openmind
import torch
import argparse
import time

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="jeffding/openchat-3.5-1210-openmind",
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
    
    
    start_time = time.time()
    
    pipe = pipeline("text-generation", model=model_path, torch_dtype=torch.bfloat16, device_map=device)

    # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
    messages = [
        {
            "role": "system",
            "content": "You are a friendly chatbot who always responds in the style of a pirate",
        },
        {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
    ]
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
    print(outputs[0]["generated_text"])
    
    end_time = time.time()
    print(f"硬件环境：{device},推理执行时间：{end_time - start_time}秒")
    
if __name__ == "__main__":
    main()

curl http://localhost:18888/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openchat_3.5",
    "messages": [{"role": "user", "content": "You are a large language model named OpenChat. Write a poem to describe yourself"}]
  }'

curl http://localhost:18888/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openchat_3.5",
    "condition": "Math Correct",
    "messages": [{"role": "user", "content": "10.3 − 7988.8133 = "}]
  }'

GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:

Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:

messages = [
    {"role": "user", "content": "Hello"},
    {"role": "assistant", "content": "Hi"},
    {"role": "user", "content": "How are you today?"}
]
tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]

###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
4. Please do not generate any other opening, closing, and explanations.

###The instruction to evaluate:
{orig_instruction}

###Response to evaluate:
{orig_response}

###Reference Answer (Score 5):
{orig_reference_answer}

###Score Rubrics:
[{orig_criteria}]
Score 1: {orig_score1_description}
Score 2: {orig_score2_description}
Score 3: {orig_score3_description}
Score 4: {orig_score4_description}
Score 5: {orig_score5_description}

###Feedback: