README.md

metadata

datasets:
  - wikipedia
language:
  - zh
  - en
tags:
  - chinese
  - english
  - TensorBlock
  - GGUF
inference:
  parameters:
    max_new_tokens: 50
    do_sample: true
widget:
  - text: 粉圓，在珍珠奶茶中也稱波霸或珍珠，是一種
pipeline_tag: text-generation
base_model: p208p2002/llama-chinese-81M

p208p2002/llama-chinese-81M - GGUF

This repo contains GGUF format model files for p208p2002/llama-chinese-81M.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Model file specification

Filename	Quant type	File Size	Description
llama-chinese-81M-Q2_K.gguf	Q2_K	0.037 GB	smallest, significant quality loss - not recommended for most purposes
llama-chinese-81M-Q3_K_S.gguf	Q3_K_S	0.042 GB	very small, high quality loss
llama-chinese-81M-Q3_K_M.gguf	Q3_K_M	0.045 GB	very small, high quality loss
llama-chinese-81M-Q3_K_L.gguf	Q3_K_L	0.047 GB	small, substantial quality loss
llama-chinese-81M-Q4_0.gguf	Q4_0	0.051 GB	legacy; small, very high quality loss - prefer using Q3_K_M
llama-chinese-81M-Q4_K_S.gguf	Q4_K_S	0.051 GB	small, greater quality loss
llama-chinese-81M-Q4_K_M.gguf	Q4_K_M	0.052 GB	medium, balanced quality - recommended
llama-chinese-81M-Q5_0.gguf	Q5_0	0.059 GB	legacy; medium, balanced quality - prefer using Q4_K_M
llama-chinese-81M-Q5_K_S.gguf	Q5_K_S	0.059 GB	large, low quality loss - recommended
llama-chinese-81M-Q5_K_M.gguf	Q5_K_M	0.060 GB	large, very low quality loss - recommended
llama-chinese-81M-Q6_K.gguf	Q6_K	0.067 GB	very large, extremely low quality loss
llama-chinese-81M-Q8_0.gguf	Q8_0	0.087 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/p208p2002_llama-chinese-81M-GGUF --include "llama-chinese-81M-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/p208p2002_llama-chinese-81M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'