TensorBlock

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

w601sxs/b1ade-1b-bf16 - GGUF

This repo contains GGUF format model files for w601sxs/b1ade-1b-bf16.

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
b1ade-1b-bf16-Q2_K.gguf Q2_K 0.420 GB smallest, significant quality loss - not recommended for most purposes
b1ade-1b-bf16-Q3_K_S.gguf Q3_K_S 0.478 GB very small, high quality loss
b1ade-1b-bf16-Q3_K_M.gguf Q3_K_M 0.552 GB very small, high quality loss
b1ade-1b-bf16-Q3_K_L.gguf Q3_K_L 0.592 GB small, substantial quality loss
b1ade-1b-bf16-Q4_0.gguf Q4_0 0.599 GB legacy; small, very high quality loss - prefer using Q3_K_M
b1ade-1b-bf16-Q4_K_S.gguf Q4_K_S 0.603 GB small, greater quality loss
b1ade-1b-bf16-Q4_K_M.gguf Q4_K_M 0.659 GB medium, balanced quality - recommended
b1ade-1b-bf16-Q5_0.gguf Q5_0 0.712 GB legacy; medium, balanced quality - prefer using Q4_K_M
b1ade-1b-bf16-Q5_K_S.gguf Q5_K_S 0.712 GB large, low quality loss - recommended
b1ade-1b-bf16-Q5_K_M.gguf Q5_K_M 0.757 GB large, very low quality loss - recommended
b1ade-1b-bf16-Q6_K.gguf Q6_K 0.833 GB very large, extremely low quality loss
b1ade-1b-bf16-Q8_0.gguf Q8_0 1.078 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/b1ade-1b-bf16-GGUF --include "b1ade-1b-bf16-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/b1ade-1b-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
193
GGUF
Model size
1.01B params
Architecture
gptneox

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/b1ade-1b-bf16-GGUF

Quantized
(1)
this model

Dataset used to train tensorblock/b1ade-1b-bf16-GGUF