Hugging Face's logo

tensorblock
/
OLMoE-1B-7B-0924-GGUF

Transformers
GGUF
English
Mixture of Experts
olmo
olmoe
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
OLMoE-1B-7B-0924-GGUF / README.md
morriszms's picture
morriszms
Update README.md
8c31793 verified
preview code
|
raw
history blame contribute delete
4.72 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - moe
  - olmo
  - olmoe
  - TensorBlock
  - GGUF
co2_eq_emissions: 1
datasets:
  - allenai/OLMoE-mix-0924
library_name: transformers
base_model: allenai/OLMoE-1B-7B-0924
TensorBlock

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

allenai/OLMoE-1B-7B-0924 - GGUF

This repo contains GGUF format model files for allenai/OLMoE-1B-7B-0924.

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
OLMoE-1B-7B-0924-Q2_K.gguf Q2_K 2.387 GB smallest, significant quality loss - not recommended for most purposes
OLMoE-1B-7B-0924-Q3_K_S.gguf Q3_K_S 2.815 GB very small, high quality loss
OLMoE-1B-7B-0924-Q3_K_M.gguf Q3_K_M 3.114 GB very small, high quality loss
OLMoE-1B-7B-0924-Q3_K_L.gguf Q3_K_L 3.363 GB small, substantial quality loss
OLMoE-1B-7B-0924-Q4_0.gguf Q4_0 3.658 GB legacy; small, very high quality loss - prefer using Q3_K_M
OLMoE-1B-7B-0924-Q4_K_S.gguf Q4_K_S 3.691 GB small, greater quality loss
OLMoE-1B-7B-0924-Q4_K_M.gguf Q4_K_M 3.924 GB medium, balanced quality - recommended
OLMoE-1B-7B-0924-Q5_0.gguf Q5_0 4.452 GB legacy; medium, balanced quality - prefer using Q4_K_M
OLMoE-1B-7B-0924-Q5_K_S.gguf Q5_K_S 4.452 GB large, low quality loss - recommended
OLMoE-1B-7B-0924-Q5_K_M.gguf Q5_K_M 4.588 GB large, very low quality loss - recommended
OLMoE-1B-7B-0924-Q6_K.gguf Q6_K 5.294 GB very large, extremely low quality loss
OLMoE-1B-7B-0924-Q8_0.gguf Q8_0 6.854 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/OLMoE-1B-7B-0924-GGUF --include "OLMoE-1B-7B-0924-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/OLMoE-1B-7B-0924-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'