TensorBlock

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

vandijklab/C2S-Pythia-410m-diverse-single-and-multi-cell-tasks - GGUF

This repo contains GGUF format model files for vandijklab/C2S-Pythia-410m-diverse-single-and-multi-cell-tasks.

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
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q2_K.gguf Q2_K 0.174 GB smallest, significant quality loss - not recommended for most purposes
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q3_K_S.gguf Q3_K_S 0.197 GB very small, high quality loss
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q3_K_M.gguf Q3_K_M 0.224 GB very small, high quality loss
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q3_K_L.gguf Q3_K_L 0.240 GB small, substantial quality loss
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q4_0.gguf Q4_0 0.244 GB legacy; small, very high quality loss - prefer using Q3_K_M
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q4_K_S.gguf Q4_K_S 0.246 GB small, greater quality loss
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q4_K_M.gguf Q4_K_M 0.267 GB medium, balanced quality - recommended
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q5_0.gguf Q5_0 0.288 GB legacy; medium, balanced quality - prefer using Q4_K_M
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q5_K_S.gguf Q5_K_S 0.288 GB large, low quality loss - recommended
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q5_K_M.gguf Q5_K_M 0.305 GB large, very low quality loss - recommended
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q6_K.gguf Q6_K 0.335 GB very large, extremely low quality loss
C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-Q8_0.gguf Q8_0 0.433 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/C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-GGUF --include "C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-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/C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
229
GGUF
Model size
405M 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/C2S-Pythia-410m-diverse-single-and-multi-cell-tasks-GGUF