Hugging Face's logo

tensorblock
/
Mistral-7B-Instruct-v0.2-sliced-24-layer-GGUF

Transformers
GGUF
#mergekit
#arcee-ai
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Mistral-7B-Instruct-v0.2-sliced-24-layer-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
aa2b434 verified
preview code
|
raw
history blame contribute delete
5.73 kB
metadata
library_name: transformers
tags:
  - '#mergekit '
  - '#arcee-ai'
  - TensorBlock
  - GGUF
datasets:
  - arcee-ai/sec-data-mini
base_model: arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer
TensorBlock

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

arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer - GGUF

This repo contains GGUF format model files for arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer.

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

Prompt template 

<s>[INST] {prompt} [/INST]

Model file specification

Filename Quant type File Size Description
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q2_K.gguf Q2_K 1.935 GB smallest, significant quality loss - not recommended for most purposes
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q3_K_S.gguf Q3_K_S 2.249 GB very small, high quality loss
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q3_K_M.gguf Q3_K_M 2.493 GB very small, high quality loss
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q3_K_L.gguf Q3_K_L 2.708 GB small, substantial quality loss
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q4_0.gguf Q4_0 2.912 GB legacy; small, very high quality loss - prefer using Q3_K_M
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q4_K_S.gguf Q4_K_S 2.935 GB small, greater quality loss
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q4_K_M.gguf Q4_K_M 3.094 GB medium, balanced quality - recommended
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q5_0.gguf Q5_0 3.537 GB legacy; medium, balanced quality - prefer using Q4_K_M
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q5_K_S.gguf Q5_K_S 3.537 GB large, low quality loss - recommended
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q5_K_M.gguf Q5_K_M 3.630 GB large, very low quality loss - recommended
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q6_K.gguf Q6_K 4.201 GB very large, extremely low quality loss
Mistral-7B-Instruct-v0.2-sliced-24-layer-Q8_0.gguf Q8_0 5.441 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/Mistral-7B-Instruct-v0.2-sliced-24-layer-GGUF --include "Mistral-7B-Instruct-v0.2-sliced-24-layer-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/Mistral-7B-Instruct-v0.2-sliced-24-layer-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'