Hugging Face's logo

tensorblock
/
JSL-MedMNX-7B-SFT-GGUF

Transformers
GGUF
English
reward model
RLHF
medical
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
JSL-MedMNX-7B-SFT-GGUF / README.md
morriszms's picture
morriszms
Update README.md
bbb54ad verified
preview code
|
raw
history blame
4.86 kB
metadata
license: cc-by-nc-nd-4.0
language:
  - en
library_name: transformers
tags:
  - reward model
  - RLHF
  - medical
  - TensorBlock
  - GGUF
base_model: johnsnowlabs/JSL-MedMNX-7B-SFT
TensorBlock

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

johnsnowlabs/JSL-MedMNX-7B-SFT - GGUF

This repo contains GGUF format model files for johnsnowlabs/JSL-MedMNX-7B-SFT.

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

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
JSL-MedMNX-7B-SFT-Q2_K.gguf Q2_K 2.533 GB smallest, significant quality loss - not recommended for most purposes
JSL-MedMNX-7B-SFT-Q3_K_S.gguf Q3_K_S 2.947 GB very small, high quality loss
JSL-MedMNX-7B-SFT-Q3_K_M.gguf Q3_K_M 3.277 GB very small, high quality loss
JSL-MedMNX-7B-SFT-Q3_K_L.gguf Q3_K_L 3.560 GB small, substantial quality loss
JSL-MedMNX-7B-SFT-Q4_0.gguf Q4_0 3.827 GB legacy; small, very high quality loss - prefer using Q3_K_M
JSL-MedMNX-7B-SFT-Q4_K_S.gguf Q4_K_S 3.856 GB small, greater quality loss
JSL-MedMNX-7B-SFT-Q4_K_M.gguf Q4_K_M 4.068 GB medium, balanced quality - recommended
JSL-MedMNX-7B-SFT-Q5_0.gguf Q5_0 4.654 GB legacy; medium, balanced quality - prefer using Q4_K_M
JSL-MedMNX-7B-SFT-Q5_K_S.gguf Q5_K_S 4.654 GB large, low quality loss - recommended
JSL-MedMNX-7B-SFT-Q5_K_M.gguf Q5_K_M 4.779 GB large, very low quality loss - recommended
JSL-MedMNX-7B-SFT-Q6_K.gguf Q6_K 5.534 GB very large, extremely low quality loss
JSL-MedMNX-7B-SFT-Q8_0.gguf Q8_0 7.167 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/JSL-MedMNX-7B-SFT-GGUF --include "JSL-MedMNX-7B-SFT-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/JSL-MedMNX-7B-SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'