cvx-coder/README.md

language, pipeline_tag

language	pipeline_tag
en	text-generation

简介

cvx-coder 增强了大模型CVX 代码能力和QA能力。它是phi-3在CVX文档, 合成代码, 论坛对话数据上的微调版本。

开始

先下载模型： Git下载

#Git模型下载
git clone https://www.modelscope.cn/tommy1235/cvx-coder.git

然后运行下面示例代码

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
m_path="你的路径/cvx-coder"
model = AutoModelForCausalLM.from_pretrained(
    m_path, 
    device_map="auto", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
tokenizer = AutoTokenizer.from_pretrained(m_path)
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
generation_args = {
    "max_new_tokens": 2000,
    "return_full_text": False,
    "temperature": 0,
    "do_sample": False,
}
content='''my problem is not convex, can i use cvx? if not, what should i do, be specific.'''
messages = [
    {"role": "user", "content": content},
]
output = pipe(messages, **generation_args)
print(output[0]['generated_text'])

若想进入聊天模式，请运行下面的代码：

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
m_path="你的路径/cvx-coder"
model = AutoModelForCausalLM.from_pretrained(
    m_path, 
    device_map="auto", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
tokenizer = AutoTokenizer.from_pretrained(m_path)
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
generation_args = {
    "max_new_tokens": 2000,
    "return_full_text": False,
    "temperature": 0,
    "do_sample": False,
}

def assistant_talk(message, history):
    message=[
        {"role": "user", "content": message},
        ]
    temp=[]
    for i in history:
        temp+=[{"role": "user", "content": i[0]},{"role": "assistant", "content": i[1]}]
        
    messages =temp  + message

    output = pipe(messages, **generation_args)
    return output[0]['generated_text']
gr.ChatInterface(assistant_talk).launch()