summit4you/Llama3-8B-COIG-CQIA-GGUF

Model Summary

Llama3-8B-COIG-CQIA is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3-8B-Instruct model.

Developed by: Wenfeng Qiu

• License: Llama-3 License
• Base Model: Meta-Llama-3-8B-Instruct
• Model Size: 8.03B
• Context length: 8K

1. Introduction

Training framework: unsloth.

Training details:

• epochs: 1
• learning rate: 2e-4
• learning rate scheduler type: linear
• warmup steps: 5
• cutoff len (i.e. context length): 2048
• global batch size: 2
• fine-tuning type: full parameters
• optimizer: adamw_8bit

2. Usage

Inference, use to llama.cpp or a UI based system like GPT4All. You can install GPT4All by going here.

Here is the example in llama.cpp.

from llama_cpp import Llama

model = Llama(
    "/Your/Path/To/Llama3-8B-COIG-CQIA.Q8_0.gguf",
    verbose=False,
    n_gpu_layers=-1,
)

system_prompt = "You are a helpful assistant."

def generate_reponse(_model, _messages, _max_tokens=8192):
    _output = _model.create_chat_completion(
        _messages,
        stop=["<|eot_id|>", "<|end_of_text|>"],
        max_tokens=_max_tokens,
    )["choices"][0]["message"]["content"]
    return _output

# The following are some examples

messages = [
    {
        "role": "system",
        "content": system_prompt,
    },
    {"role": "user", "content": "你是谁？"},
]


print(generate_reponse(_model=model, _messages=messages), end="\n\n\n")