Hugging Face's logo

tensorblock
/
openchat_3.5-GGUF

Text Generation
Transformers
GGUF
openchat
mistral
C-RLFT
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
openchat_3.5-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
2a332b3 verified
preview code
|
raw
history blame contribute delete
4.92 kB
metadata
license: apache-2.0
tags:
  - openchat
  - mistral
  - C-RLFT
  - TensorBlock
  - GGUF
datasets:
  - openchat/openchat_sharegpt4_dataset
  - imone/OpenOrca_FLAN
  - LDJnr/LessWrong-Amplify-Instruct
  - LDJnr/Pure-Dove
  - LDJnr/Verified-Camel
  - tiedong/goat
  - glaiveai/glaive-code-assistant
  - meta-math/MetaMathQA
  - OpenAssistant/oasst_top1_2023-08-25
  - TIGER-Lab/MathInstruct
library_name: transformers
pipeline_tag: text-generation
base_model: openchat/openchat_3.5
TensorBlock

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

openchat/openchat_3.5 - GGUF

This repo contains GGUF format model files for openchat/openchat_3.5.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template 

<s>GPT4 Correct System: {system_prompt}<|end_of_turn|>GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:

Model file specification

Filename Quant type File Size Description
openchat_3.5-Q2_K.gguf Q2_K 2.719 GB smallest, significant quality loss - not recommended for most purposes
openchat_3.5-Q3_K_S.gguf Q3_K_S 3.165 GB very small, high quality loss
openchat_3.5-Q3_K_M.gguf Q3_K_M 3.519 GB very small, high quality loss
openchat_3.5-Q3_K_L.gguf Q3_K_L 3.822 GB small, substantial quality loss
openchat_3.5-Q4_0.gguf Q4_0 4.109 GB legacy; small, very high quality loss - prefer using Q3_K_M
openchat_3.5-Q4_K_S.gguf Q4_K_S 4.140 GB small, greater quality loss
openchat_3.5-Q4_K_M.gguf Q4_K_M 4.368 GB medium, balanced quality - recommended
openchat_3.5-Q5_0.gguf Q5_0 4.998 GB legacy; medium, balanced quality - prefer using Q4_K_M
openchat_3.5-Q5_K_S.gguf Q5_K_S 4.998 GB large, low quality loss - recommended
openchat_3.5-Q5_K_M.gguf Q5_K_M 5.131 GB large, very low quality loss - recommended
openchat_3.5-Q6_K.gguf Q6_K 5.942 GB very large, extremely low quality loss
openchat_3.5-Q8_0.gguf Q8_0 7.696 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/openchat_3.5-GGUF --include "openchat_3.5-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/openchat_3.5-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'