Hugging Face's logo

tensorblock
/
NuExtract-1.5-smol-GGUF

Text Generation
GGUF
multilingual
nlp
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
1
NuExtract-1.5-smol-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
71c3ed5 verified
preview code
|
raw
history blame contribute delete
4.75 kB
metadata
license: mit
language:
  - multilingual
tags:
  - nlp
  - TensorBlock
  - GGUF
base_model: numind/NuExtract-1.5-smol
pipeline_tag: text-generation
inference: true
TensorBlock

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

numind/NuExtract-1.5-smol - GGUF

This repo contains GGUF format model files for numind/NuExtract-1.5-smol.

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
NuExtract-1.5-smol-Q2_K.gguf Q2_K 0.675 GB smallest, significant quality loss - not recommended for most purposes
NuExtract-1.5-smol-Q3_K_S.gguf Q3_K_S 0.777 GB very small, high quality loss
NuExtract-1.5-smol-Q3_K_M.gguf Q3_K_M 0.860 GB very small, high quality loss
NuExtract-1.5-smol-Q3_K_L.gguf Q3_K_L 0.933 GB small, substantial quality loss
NuExtract-1.5-smol-Q4_0.gguf Q4_0 0.991 GB legacy; small, very high quality loss - prefer using Q3_K_M
NuExtract-1.5-smol-Q4_K_S.gguf Q4_K_S 0.999 GB small, greater quality loss
NuExtract-1.5-smol-Q4_K_M.gguf Q4_K_M 1.056 GB medium, balanced quality - recommended
NuExtract-1.5-smol-Q5_0.gguf Q5_0 1.192 GB legacy; medium, balanced quality - prefer using Q4_K_M
NuExtract-1.5-smol-Q5_K_S.gguf Q5_K_S 1.192 GB large, low quality loss - recommended
NuExtract-1.5-smol-Q5_K_M.gguf Q5_K_M 1.225 GB large, very low quality loss - recommended
NuExtract-1.5-smol-Q6_K.gguf Q6_K 1.406 GB very large, extremely low quality loss
NuExtract-1.5-smol-Q8_0.gguf Q8_0 1.820 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/NuExtract-1.5-smol-GGUF --include "NuExtract-1.5-smol-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/NuExtract-1.5-smol-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'