基于GPT4All本地安装LLM训练_gpt4all 如何训练

​

import gpt4all
 
gptj = gpt4all.GPT4All("ggml-gpt4all-j-v1.3-groovy")
messages = [{"role": "user", "content": "Give me a list of 10 colors and their RGB code"}]
ret = gptj.chat_completion(messages)
print(ret)

 
{'model': 'ggml-gpt4all-j-v1.3-groovy',
 'usage': {'prompt_tokens': 272,
           'completion_tokens': 301,
           'total_tokens': 573},
 'choices': [
    {'message':
        {'role': 'assistant',
         'content': ' Here is a list of 10 colors and their RGB code:Red (255, 0, 0)  Green (0, 255, 0) Blue (0, 0, 255)  Yellow (255, 255, 0) Orange (255, 127, 0)  Purple (0, 128, 255) Pink (255, 192, 203)  Blue-Green (0, 0, 255)  Green-Blue (0, 0, 255)  Blue-Purple (0, 0, 255)  Blue-Green (0, 0, 255)  Blue-Purple (0, 0'
        }
    }
 ]
}

import json
import gpt4all
 
gptj = gpt4all.GPT4All("ggml-gpt4all-j-v1.3-groovy")
messages = [{"role": "user", "content": "Can you explain what is a large language model?"}]
ret = gptj.chat_completion(messages)
 
messages.append(ret["choices"][0]["message"])
messages.append({"role": "user", "content": "Can you give some examples applications?"})
ret = gptj.chat_completion(messages)
 
messages.append(ret["choices"][0]["message"])
messages.append({"role": "user", "content": "Are there any limitations?"})
ret = gptj.chat_completion(messages)
 
messages.append(ret["choices"][0]["message"])
messages.append({"role": "user", "content": "Summarize the above in two sentences."})
ret = gptj.chat_completion(messages)
 
print(json.dumps(messages, indent=4))
print(json.dumps(ret, indent=4))

[
    {
        "role": "user",
        "content": "Can you explain what is a large language model?"
    },
    {
        "role": "assistant",
        "content": " A large language model is a type of artificial intelligence that can process and understand natural language, such as speech or text. It is trained on large amounts of data and can perform tasks such as language translation, sentiment analysis or even answering questions. Large language models are becoming increasingly popular in various industries, including finance and healthcare."
    },
    {
        "role": "user",
        "content": "Can you give some examples applications?"
    },
    {
        "role": "assistant",
        "content": "  Large language models are being used in a variety of applications, such as:- Language translation and machine translation, where large language models are trained on vast amounts of data to improve accuracy and speed.- Sentiment analysis, where large language models are trained to analyze social media data and identify patterns in user opinions.- Question answering, where large language models are trained to answer questions based on a large corpus of data.- Healthcare, where large language models are being used to analyze patient data and identify patterns in health trends.- Finance, where large language models are being used to analyze financial data and identify patterns in"
    },
    {
        "role": "user",
        "content": "Are there any limitations?"
    },
    {
        "role": "assistant",
        "content": "  Yes, there are some limitations to large language models. One of the main challenges is that they require a lot of data to train, which can be expensive and time-consuming. Additionally, large language models can be computationally expensive and may require specialized hardware to run. Another limitation is that large language models may not be able to understand the nuances of human language, which can make them less effective in certain situations. Finally, large language models may not be able to understand the context of a conversation or text, which can make them less effective in certain applications."
    },
    {
        "role": "user",
        "content": "Summarize the above in two sentences."
    }
]
{
    "model": "ggml-gpt4all-j-v1.3-groovy",
    "usage": {
        "prompt_tokens": 2113,
        "completion_tokens": 542,
        "total_tokens": 2655
    },
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "  Large language models are a type of artificial intelligence that can process and understand natural language, such as speech or text. They are trained on large amounts of data and can perform tasks such as language translation, sentiment analysis or even answering questions. They are becoming increasingly popular in various industries, including finance and healthcare. However, there are some limitations such as expensive data and specialized hardware, computational expense, lack of understanding nuances in human language and context."
            }
        }
    ]
}