Text Generation
Transformers
GGUF
English
code
TensorBlock
GGUF
Eval Results
Inference Endpoints
TensorBlock

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

smallcloudai/Refact-1_6B-fim - GGUF

This repo contains GGUF format model files for smallcloudai/Refact-1_6B-fim.

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
Refact-1_6B-fim-Q2_K.gguf Q2_K 0.581 GB smallest, significant quality loss - not recommended for most purposes
Refact-1_6B-fim-Q3_K_S.gguf Q3_K_S 0.673 GB very small, high quality loss
Refact-1_6B-fim-Q3_K_M.gguf Q3_K_M 0.739 GB very small, high quality loss
Refact-1_6B-fim-Q3_K_L.gguf Q3_K_L 0.795 GB small, substantial quality loss
Refact-1_6B-fim-Q4_0.gguf Q4_0 0.857 GB legacy; small, very high quality loss - prefer using Q3_K_M
Refact-1_6B-fim-Q4_K_S.gguf Q4_K_S 0.862 GB small, greater quality loss
Refact-1_6B-fim-Q4_K_M.gguf Q4_K_M 0.902 GB medium, balanced quality - recommended
Refact-1_6B-fim-Q5_0.gguf Q5_0 1.030 GB legacy; medium, balanced quality - prefer using Q4_K_M
Refact-1_6B-fim-Q5_K_S.gguf Q5_K_S 1.030 GB large, low quality loss - recommended
Refact-1_6B-fim-Q5_K_M.gguf Q5_K_M 1.053 GB large, very low quality loss - recommended
Refact-1_6B-fim-Q6_K.gguf Q6_K 1.214 GB very large, extremely low quality loss
Refact-1_6B-fim-Q8_0.gguf Q8_0 1.571 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/Refact-1_6B-fim-GGUF --include "Refact-1_6B-fim-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/Refact-1_6B-fim-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
53
GGUF
Model size
1.59B params
Architecture
refact

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tensorblock/Refact-1_6B-fim-GGUF

Quantized
(3)
this model

Datasets used to train tensorblock/Refact-1_6B-fim-GGUF

Evaluation results