OLMo-1B-hf-GGUF / README.md
morriszms's picture
Update README.md
fe39a07 verified
metadata
license: apache-2.0
datasets:
  - allenai/dolma
language:
  - en
tags:
  - TensorBlock
  - GGUF
base_model: allenai/OLMo-1B-hf
TensorBlock

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

allenai/OLMo-1B-hf - GGUF

This repo contains GGUF format model files for allenai/OLMo-1B-hf.

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
OLMo-1B-hf-Q2_K.gguf Q2_K 0.447 GB smallest, significant quality loss - not recommended for most purposes
OLMo-1B-hf-Q3_K_S.gguf Q3_K_S 0.510 GB very small, high quality loss
OLMo-1B-hf-Q3_K_M.gguf Q3_K_M 0.563 GB very small, high quality loss
OLMo-1B-hf-Q3_K_L.gguf Q3_K_L 0.607 GB small, substantial quality loss
OLMo-1B-hf-Q4_0.gguf Q4_0 0.643 GB legacy; small, very high quality loss - prefer using Q3_K_M
OLMo-1B-hf-Q4_K_S.gguf Q4_K_S 0.649 GB small, greater quality loss
OLMo-1B-hf-Q4_K_M.gguf Q4_K_M 0.683 GB medium, balanced quality - recommended
OLMo-1B-hf-Q5_0.gguf Q5_0 0.768 GB legacy; medium, balanced quality - prefer using Q4_K_M
OLMo-1B-hf-Q5_K_S.gguf Q5_K_S 0.768 GB large, low quality loss - recommended
OLMo-1B-hf-Q5_K_M.gguf Q5_K_M 0.789 GB large, very low quality loss - recommended
OLMo-1B-hf-Q6_K.gguf Q6_K 0.901 GB very large, extremely low quality loss
OLMo-1B-hf-Q8_0.gguf Q8_0 1.166 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/OLMo-1B-hf-GGUF --include "OLMo-1B-hf-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/OLMo-1B-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'