Hugging Face's logo

tensorblock
/
AMD-OLMo-1B-SFT-GGUF

Text Generation
Transformers
GGUF
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
AMD-OLMo-1B-SFT-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
1a4f8a7 verified
preview code
|
raw
history blame
4.62 kB
metadata
license: apache-2.0
datasets:
  - allenai/dolma
pipeline_tag: text-generation
library_name: transformers
tags:
  - TensorBlock
  - GGUF
base_model: amd/AMD-OLMo-1B-SFT
TensorBlock

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

amd/AMD-OLMo-1B-SFT - GGUF

This repo contains GGUF format model files for amd/AMD-OLMo-1B-SFT.

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
AMD-OLMo-1B-SFT-Q2_K.gguf Q2_K 0.480 GB smallest, significant quality loss - not recommended for most purposes
AMD-OLMo-1B-SFT-Q3_K_S.gguf Q3_K_S 0.548 GB very small, high quality loss
AMD-OLMo-1B-SFT-Q3_K_M.gguf Q3_K_M 0.604 GB very small, high quality loss
AMD-OLMo-1B-SFT-Q3_K_L.gguf Q3_K_L 0.651 GB small, substantial quality loss
AMD-OLMo-1B-SFT-Q4_0.gguf Q4_0 0.690 GB legacy; small, very high quality loss - prefer using Q3_K_M
AMD-OLMo-1B-SFT-Q4_K_S.gguf Q4_K_S 0.697 GB small, greater quality loss
AMD-OLMo-1B-SFT-Q4_K_M.gguf Q4_K_M 0.734 GB medium, balanced quality - recommended
AMD-OLMo-1B-SFT-Q5_0.gguf Q5_0 0.824 GB legacy; medium, balanced quality - prefer using Q4_K_M
AMD-OLMo-1B-SFT-Q5_K_S.gguf Q5_K_S 0.824 GB large, low quality loss - recommended
AMD-OLMo-1B-SFT-Q5_K_M.gguf Q5_K_M 0.847 GB large, very low quality loss - recommended
AMD-OLMo-1B-SFT-Q6_K.gguf Q6_K 0.967 GB very large, extremely low quality loss
AMD-OLMo-1B-SFT-Q8_0.gguf Q8_0 1.252 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/AMD-OLMo-1B-SFT-GGUF --include "AMD-OLMo-1B-SFT-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/AMD-OLMo-1B-SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'