GGUF
Japanese
English
TensorBlock
GGUF
Inference Endpoints
conversational
Edit model card
TensorBlock

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

augmxnt/shisa-7b-v1 - GGUF

This repo contains GGUF format model files for augmxnt/shisa-7b-v1.

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

Prompt template

<s>[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]

Model file specification

Filename Quant type File Size Description
shisa-7b-v1-Q2_K.gguf Q2_K 2.921 GB smallest, significant quality loss - not recommended for most purposes
shisa-7b-v1-Q3_K_S.gguf Q3_K_S 3.370 GB very small, high quality loss
shisa-7b-v1-Q3_K_M.gguf Q3_K_M 3.700 GB very small, high quality loss
shisa-7b-v1-Q3_K_L.gguf Q3_K_L 3.982 GB small, substantial quality loss
shisa-7b-v1-Q4_0.gguf Q4_0 4.294 GB legacy; small, very high quality loss - prefer using Q3_K_M
shisa-7b-v1-Q4_K_S.gguf Q4_K_S 4.323 GB small, greater quality loss
shisa-7b-v1-Q4_K_M.gguf Q4_K_M 4.535 GB medium, balanced quality - recommended
shisa-7b-v1-Q5_0.gguf Q5_0 5.164 GB legacy; medium, balanced quality - prefer using Q4_K_M
shisa-7b-v1-Q5_K_S.gguf Q5_K_S 5.164 GB large, low quality loss - recommended
shisa-7b-v1-Q5_K_M.gguf Q5_K_M 5.288 GB large, very low quality loss - recommended
shisa-7b-v1-Q6_K.gguf Q6_K 6.088 GB very large, extremely low quality loss
shisa-7b-v1-Q8_0.gguf Q8_0 7.884 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/shisa-7b-v1-GGUF --include "shisa-7b-v1-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/shisa-7b-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
0
GGUF
Model size
7.96B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/shisa-7b-v1-GGUF

Quantized
(3)
this model

Datasets used to train tensorblock/shisa-7b-v1-GGUF