Hugging Face's logo

tensorblock
/
MiniCPM-2B-128k-GGUF

Text Generation
Transformers
GGUF
Chinese
English
MiniCPM
ModelBest
THUNLP
conversational
custom_code
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
MiniCPM-2B-128k-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
e1f1044 verified
preview code
|
raw
history blame contribute delete
4.81 kB
metadata
datasets:
  - stingning/ultrachat
language:
  - zh
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - MiniCPM
  - ModelBest
  - THUNLP
  - conversational
  - custom_code
  - TensorBlock
  - GGUF
base_model: openbmb/MiniCPM-2B-128k
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

openbmb/MiniCPM-2B-128k - GGUF

This repo contains GGUF format model files for openbmb/MiniCPM-2B-128k.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
MiniCPM-2B-128k-Q2_K.gguf Q2_K 1.297 GB smallest, significant quality loss - not recommended for most purposes
MiniCPM-2B-128k-Q3_K_S.gguf Q3_K_S 1.477 GB very small, high quality loss
MiniCPM-2B-128k-Q3_K_M.gguf Q3_K_M 1.603 GB very small, high quality loss
MiniCPM-2B-128k-Q3_K_L.gguf Q3_K_L 1.686 GB small, substantial quality loss
MiniCPM-2B-128k-Q4_0.gguf Q4_0 1.768 GB legacy; small, very high quality loss - prefer using Q3_K_M
MiniCPM-2B-128k-Q4_K_S.gguf Q4_K_S 1.841 GB small, greater quality loss
MiniCPM-2B-128k-Q4_K_M.gguf Q4_K_M 1.962 GB medium, balanced quality - recommended
MiniCPM-2B-128k-Q5_0.gguf Q5_0 2.109 GB legacy; medium, balanced quality - prefer using Q4_K_M
MiniCPM-2B-128k-Q5_K_S.gguf Q5_K_S 2.142 GB large, low quality loss - recommended
MiniCPM-2B-128k-Q5_K_M.gguf Q5_K_M 2.239 GB large, very low quality loss - recommended
MiniCPM-2B-128k-Q6_K.gguf Q6_K 2.599 GB very large, extremely low quality loss
MiniCPM-2B-128k-Q8_0.gguf Q8_0 3.199 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/MiniCPM-2B-128k-GGUF --include "MiniCPM-2B-128k-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/MiniCPM-2B-128k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'