TensorBlock

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

Azure99/blossom-v5.1-9b - GGUF

This repo contains GGUF format model files for Azure99/blossom-v5.1-9b.

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

Prompt template

A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: {prompt}
|Bot|: 

Model file specification

Filename Quant type File Size Description
blossom-v5.1-9b-Q2_K.gguf Q2_K 3.354 GB smallest, significant quality loss - not recommended for most purposes
blossom-v5.1-9b-Q3_K_S.gguf Q3_K_S 3.899 GB very small, high quality loss
blossom-v5.1-9b-Q3_K_M.gguf Q3_K_M 4.324 GB very small, high quality loss
blossom-v5.1-9b-Q3_K_L.gguf Q3_K_L 4.691 GB small, substantial quality loss
blossom-v5.1-9b-Q4_0.gguf Q4_0 5.037 GB legacy; small, very high quality loss - prefer using Q3_K_M
blossom-v5.1-9b-Q4_K_S.gguf Q4_K_S 5.072 GB small, greater quality loss
blossom-v5.1-9b-Q4_K_M.gguf Q4_K_M 5.329 GB medium, balanced quality - recommended
blossom-v5.1-9b-Q5_0.gguf Q5_0 6.108 GB legacy; medium, balanced quality - prefer using Q4_K_M
blossom-v5.1-9b-Q5_K_S.gguf Q5_K_S 6.108 GB large, low quality loss - recommended
blossom-v5.1-9b-Q5_K_M.gguf Q5_K_M 6.258 GB large, very low quality loss - recommended
blossom-v5.1-9b-Q6_K.gguf Q6_K 7.246 GB very large, extremely low quality loss
blossom-v5.1-9b-Q8_0.gguf Q8_0 9.384 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/blossom-v5.1-9b-GGUF --include "blossom-v5.1-9b-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/blossom-v5.1-9b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
169
GGUF
Model size
8.83B 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/blossom-v5.1-9b-GGUF

Quantized
(2)
this model

Datasets used to train tensorblock/blossom-v5.1-9b-GGUF