Hugging Face's logo

tensorblock
/
bloom-1b7-GGUF

Text Generation
GGUF
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
bloom-1b7-GGUF / README.md
morriszms's picture
morriszms
Update README.md
9be814f verified
preview code
|
raw
history blame contribute delete
4.61 kB
metadata
license: bigscience-bloom-rail-1.0
language:
  - ak
  - ar
  - as
  - bm
  - bn
  - ca
  - code
  - en
  - es
  - eu
  - fon
  - fr
  - gu
  - hi
  - id
  - ig
  - ki
  - kn
  - lg
  - ln
  - ml
  - mr
  - ne
  - nso
  - ny
  - or
  - pa
  - pt
  - rn
  - rw
  - sn
  - st
  - sw
  - ta
  - te
  - tn
  - ts
  - tum
  - tw
  - ur
  - vi
  - wo
  - xh
  - yo
  - zh
  - zhs
  - zht
  - zu
pipeline_tag: text-generation
base_model: bigscience/bloom-1b7
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

bigscience/bloom-1b7 - GGUF

This repo contains GGUF format model files for bigscience/bloom-1b7.

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

Prompt template

Model file specification

Filename Quant type File Size Description
bloom-1b7-Q2_K.gguf Q2_K 0.980 GB smallest, significant quality loss - not recommended for most purposes
bloom-1b7-Q3_K_S.gguf Q3_K_S 1.096 GB very small, high quality loss
bloom-1b7-Q3_K_M.gguf Q3_K_M 1.197 GB very small, high quality loss
bloom-1b7-Q3_K_L.gguf Q3_K_L 1.254 GB small, substantial quality loss
bloom-1b7-Q4_0.gguf Q4_0 1.309 GB legacy; small, very high quality loss - prefer using Q3_K_M
bloom-1b7-Q4_K_S.gguf Q4_K_S 1.315 GB small, greater quality loss
bloom-1b7-Q4_K_M.gguf Q4_K_M 1.392 GB medium, balanced quality - recommended
bloom-1b7-Q5_0.gguf Q5_0 1.509 GB legacy; medium, balanced quality - prefer using Q4_K_M
bloom-1b7-Q5_K_S.gguf Q5_K_S 1.509 GB large, low quality loss - recommended
bloom-1b7-Q5_K_M.gguf Q5_K_M 1.571 GB large, very low quality loss - recommended
bloom-1b7-Q6_K.gguf Q6_K 1.722 GB very large, extremely low quality loss
bloom-1b7-Q8_0.gguf Q8_0 2.226 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/bloom-1b7-GGUF --include "bloom-1b7-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/bloom-1b7-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'