QuantFactory/Llama3.1-8B-Chinese-Chat-GGUF

This is quantized version of shenzhi-wang/Llama3.1-8B-Chinese-Chat created using llama.cpp

Original Model Card

For optimal performance, we refrain from fine-tuning the model's identity. Thus, inquiries such as "Who are you" or "Who developed you" may yield random responses that are not necessarily accurate.

If you enjoy our model, please give it a star on our Hugging Face repo and kindly cite our model. Your support means a lot to us. Thank you!

Updates

Model Summary

llama3.1-8B-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3.1-8B-Instruct model.

Developers: Shenzhi Wang*, Yaowei Zheng*, Guoyin Wang (in.ai), Shiji Song, Gao Huang. (*: Equal Contribution)

1. Introduction

This is the first model specifically fine-tuned for Chinese & English users based on the Meta-Llama-3.1-8B-Instruct model. The fine-tuning algorithm used is ORPO [1].

[1] Hong, Jiwoo, Noah Lee, and James Thorne. "Reference-free Monolithic Preference Optimization with Odds Ratio." arXiv preprint arXiv:2403.07691 (2024).

Training framework: LLaMA-Factory.

Training details:

  • epochs: 3
  • learning rate: 3e-6
  • learning rate scheduler type: cosine
  • Warmup ratio: 0.1
  • cutoff len (i.e. context length): 8192
  • orpo beta (i.e. $\lambda$ in the ORPO paper): 0.05
  • global batch size: 128
  • fine-tuning type: full parameters
  • optimizer: paged_adamw_32bit

2. Usage

2.1 Usage of Our BF16 Model

  1. Please upgrade the transformers package to ensure it supports Llama3.1 models. The current version we are using is 4.43.0.

  2. Use the following Python script to download our BF16 model

from huggingface_hub import snapshot_download
snapshot_download(repo_id="shenzhi-wang/Llama3.1-8B-Chinese-Chat", ignore_patterns=["*.gguf"])  # Download our BF16 model without downloading GGUF models.
  1. Inference with the BF16 model
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "/Your/Local/Path/to/Llama3.1-8B-Chinese-Chat"
dtype = torch.bfloat16

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda",
    torch_dtype=dtype,
)

chat = [
    {"role": "user", "content": "ๅ†™ไธ€้ฆ–ๅ…ณไบŽๆœบๅ™จๅญฆไน ็š„่ฏ—ใ€‚"},
]
input_ids = tokenizer.apply_chat_template(
    chat, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=8192,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1] :]
print(tokenizer.decode(response, skip_special_tokens=True))

2.2 Usage of Our GGUF Models

  1. Download our GGUF models from the gguf_models folder;
  2. Use the GGUF models with LM Studio;
  3. You can also follow the instructions from https://github.com/ggerganov/llama.cpp/tree/master#usage to use gguf models.

Citation

If our Llama3.1-8B-Chinese-Chat is helpful, please kindly cite as:

@misc {shenzhi_wang_2024,
    author       = { Wang, Shenzhi and Zheng, Yaowei and Wang, Guoyin and Song, Shiji and Huang, Gao },
    title        = { Llama3.1-8B-Chinese-Chat },
    year         = 2024,
    url          = { https://huggingface.co./shenzhi-wang/Llama3.1-8B-Chinese-Chat },
    doi          = { 10.57967/hf/2779 },
    publisher    = { Hugging Face }
}
Downloads last month
624
GGUF
Model size
8.03B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for QuantFactory/Llama3.1-8B-Chinese-Chat-GGUF

Quantized
(300)
this model