Hugging Face's logo

tensorblock
/
stablelm-2-12b-GGUF

GGUF
causal-lm
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
stablelm-2-12b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
0be3b28 verified
preview code
|
raw
history blame contribute delete
4.78 kB
metadata
language:
  - en
  - de
  - es
  - fr
  - it
  - nl
  - pt
license: other
tags:
  - causal-lm
  - TensorBlock
  - GGUF
datasets:
  - tiiuae/falcon-refinedweb
  - togethercomputer/RedPajama-Data-1T
  - uonlp/CulturaX
  - CarperAI/pilev2-dev
  - bigcode/starcoderdata
  - DataProvenanceInitiative/Commercially-Verified-Licenses
base_model: stabilityai/stablelm-2-12b
TensorBlock

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

stabilityai/stablelm-2-12b - GGUF

This repo contains GGUF format model files for stabilityai/stablelm-2-12b.

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

Prompt template

Model file specification

Filename Quant type File Size Description
stablelm-2-12b-Q2_K.gguf Q2_K 4.699 GB smallest, significant quality loss - not recommended for most purposes
stablelm-2-12b-Q3_K_S.gguf Q3_K_S 5.424 GB very small, high quality loss
stablelm-2-12b-Q3_K_M.gguf Q3_K_M 5.994 GB very small, high quality loss
stablelm-2-12b-Q3_K_L.gguf Q3_K_L 6.492 GB small, substantial quality loss
stablelm-2-12b-Q4_0.gguf Q4_0 6.969 GB legacy; small, very high quality loss - prefer using Q3_K_M
stablelm-2-12b-Q4_K_S.gguf Q4_K_S 7.016 GB small, greater quality loss
stablelm-2-12b-Q4_K_M.gguf Q4_K_M 7.368 GB medium, balanced quality - recommended
stablelm-2-12b-Q5_0.gguf Q5_0 8.422 GB legacy; medium, balanced quality - prefer using Q4_K_M
stablelm-2-12b-Q5_K_S.gguf Q5_K_S 8.422 GB large, low quality loss - recommended
stablelm-2-12b-Q5_K_M.gguf Q5_K_M 8.628 GB large, very low quality loss - recommended
stablelm-2-12b-Q6_K.gguf Q6_K 9.967 GB very large, extremely low quality loss
stablelm-2-12b-Q8_0.gguf Q8_0 12.908 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/stablelm-2-12b-GGUF --include "stablelm-2-12b-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/stablelm-2-12b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'