Edit model card
TensorBlock

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

DeepMount00/Minerva-3B-base-RAG - GGUF

This repo contains GGUF format model files for DeepMount00/Minerva-3B-base-RAG.

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
Minerva-3B-base-RAG-Q2_K.gguf Q2_K 1.025 GB smallest, significant quality loss - not recommended for most purposes
Minerva-3B-base-RAG-Q3_K_S.gguf Q3_K_S 1.190 GB very small, high quality loss
Minerva-3B-base-RAG-Q3_K_M.gguf Q3_K_M 1.319 GB very small, high quality loss
Minerva-3B-base-RAG-Q3_K_L.gguf Q3_K_L 1.429 GB small, substantial quality loss
Minerva-3B-base-RAG-Q4_0.gguf Q4_0 1.538 GB legacy; small, very high quality loss - prefer using Q3_K_M
Minerva-3B-base-RAG-Q4_K_S.gguf Q4_K_S 1.549 GB small, greater quality loss
Minerva-3B-base-RAG-Q4_K_M.gguf Q4_K_M 1.632 GB medium, balanced quality - recommended
Minerva-3B-base-RAG-Q5_0.gguf Q5_0 1.865 GB legacy; medium, balanced quality - prefer using Q4_K_M
Minerva-3B-base-RAG-Q5_K_S.gguf Q5_K_S 1.865 GB large, low quality loss - recommended
Minerva-3B-base-RAG-Q5_K_M.gguf Q5_K_M 1.913 GB large, very low quality loss - recommended
Minerva-3B-base-RAG-Q6_K.gguf Q6_K 2.212 GB very large, extremely low quality loss
Minerva-3B-base-RAG-Q8_0.gguf Q8_0 2.865 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/Minerva-3B-base-RAG-GGUF --include "Minerva-3B-base-RAG-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/Minerva-3B-base-RAG-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
217
GGUF
Model size
2.89B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/Minerva-3B-base-RAG-GGUF

Quantized
(4)
this model

Dataset used to train tensorblock/Minerva-3B-base-RAG-GGUF