Hugging Face's logo

tensorblock
/
openbuddy-mistral2-7b-v20.3-32k-GGUF

Text Generation
Transformers
GGUF
TensorBlock
GGUF
conversational
Model card Files Community
openbuddy-mistral2-7b-v20.3-32k-GGUF / README.md
morriszms's picture
morriszms
Update README.md
b334b93 verified
preview code
|
raw
history blame contribute delete
5.42 kB
metadata
language:
  - zh
  - en
  - fr
  - de
  - ja
  - ko
  - it
  - ru
pipeline_tag: text-generation
inference: false
library_name: transformers
license: apache-2.0
base_model: OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

OpenBuddy/openbuddy-mistral2-7b-v20.3-32k - GGUF

This repo contains GGUF format model files for OpenBuddy/openbuddy-mistral2-7b-v20.3-32k.

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

Prompt template 

{system_prompt}
User: {prompt}
Assistant:

Model file specification

Filename Quant type File Size Description
openbuddy-mistral2-7b-v20.3-32k-Q2_K.gguf Q2_K 2.553 GB smallest, significant quality loss - not recommended for most purposes
openbuddy-mistral2-7b-v20.3-32k-Q3_K_S.gguf Q3_K_S 2.969 GB very small, high quality loss
openbuddy-mistral2-7b-v20.3-32k-Q3_K_M.gguf Q3_K_M 3.299 GB very small, high quality loss
openbuddy-mistral2-7b-v20.3-32k-Q3_K_L.gguf Q3_K_L 3.582 GB small, substantial quality loss
openbuddy-mistral2-7b-v20.3-32k-Q4_0.gguf Q4_0 3.851 GB legacy; small, very high quality loss - prefer using Q3_K_M
openbuddy-mistral2-7b-v20.3-32k-Q4_K_S.gguf Q4_K_S 3.880 GB small, greater quality loss
openbuddy-mistral2-7b-v20.3-32k-Q4_K_M.gguf Q4_K_M 4.093 GB medium, balanced quality - recommended
openbuddy-mistral2-7b-v20.3-32k-Q5_0.gguf Q5_0 4.681 GB legacy; medium, balanced quality - prefer using Q4_K_M
openbuddy-mistral2-7b-v20.3-32k-Q5_K_S.gguf Q5_K_S 4.681 GB large, low quality loss - recommended
openbuddy-mistral2-7b-v20.3-32k-Q5_K_M.gguf Q5_K_M 4.806 GB large, very low quality loss - recommended
openbuddy-mistral2-7b-v20.3-32k-Q6_K.gguf Q6_K 5.563 GB very large, extremely low quality loss
openbuddy-mistral2-7b-v20.3-32k-Q8_0.gguf Q8_0 7.205 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/openbuddy-mistral2-7b-v20.3-32k-GGUF --include "openbuddy-mistral2-7b-v20.3-32k-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/openbuddy-mistral2-7b-v20.3-32k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'