TensorBlock

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

HuggingFaceFW/ablation-model-fineweb-v1 - GGUF

This repo contains GGUF format model files for HuggingFaceFW/ablation-model-fineweb-v1.

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
ablation-model-fineweb-v1-Q2_K.gguf Q2_K 0.676 GB smallest, significant quality loss - not recommended for most purposes
ablation-model-fineweb-v1-Q3_K_S.gguf Q3_K_S 0.779 GB very small, high quality loss
ablation-model-fineweb-v1-Q3_K_M.gguf Q3_K_M 0.862 GB very small, high quality loss
ablation-model-fineweb-v1-Q3_K_L.gguf Q3_K_L 0.934 GB small, substantial quality loss
ablation-model-fineweb-v1-Q4_0.gguf Q4_0 0.993 GB legacy; small, very high quality loss - prefer using Q3_K_M
ablation-model-fineweb-v1-Q4_K_S.gguf Q4_K_S 1.001 GB small, greater quality loss
ablation-model-fineweb-v1-Q4_K_M.gguf Q4_K_M 1.057 GB medium, balanced quality - recommended
ablation-model-fineweb-v1-Q5_0.gguf Q5_0 1.194 GB legacy; medium, balanced quality - prefer using Q4_K_M
ablation-model-fineweb-v1-Q5_K_S.gguf Q5_K_S 1.194 GB large, low quality loss - recommended
ablation-model-fineweb-v1-Q5_K_M.gguf Q5_K_M 1.227 GB large, very low quality loss - recommended
ablation-model-fineweb-v1-Q6_K.gguf Q6_K 1.408 GB very large, extremely low quality loss
ablation-model-fineweb-v1-Q8_0.gguf Q8_0 1.823 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/ablation-model-fineweb-v1-GGUF --include "ablation-model-fineweb-v1-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/ablation-model-fineweb-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
197
GGUF
Model size
1.71B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tensorblock/ablation-model-fineweb-v1-GGUF

Quantized
(1)
this model