tensorblock/llama2-merge-v0.3-GGUF

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

lIlBrother/llama2-merge-v0.3 - GGUF

This repo contains GGUF format model files for lIlBrother/llama2-merge-v0.3.

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
llama2-merge-v0.3-Q2_K.gguf	Q2_K	4.600 GB	smallest, significant quality loss - not recommended for most purposes
llama2-merge-v0.3-Q3_K_S.gguf	Q3_K_S	5.356 GB	very small, high quality loss
llama2-merge-v0.3-Q3_K_M.gguf	Q3_K_M	5.988 GB	very small, high quality loss
llama2-merge-v0.3-Q3_K_L.gguf	Q3_K_L	6.539 GB	small, substantial quality loss
llama2-merge-v0.3-Q4_0.gguf	Q4_0	6.955 GB	legacy; small, very high quality loss - prefer using Q3_K_M
llama2-merge-v0.3-Q4_K_S.gguf	Q4_K_S	7.008 GB	small, greater quality loss
llama2-merge-v0.3-Q4_K_M.gguf	Q4_K_M	7.421 GB	medium, balanced quality - recommended
llama2-merge-v0.3-Q5_0.gguf	Q5_0	8.459 GB	legacy; medium, balanced quality - prefer using Q4_K_M
llama2-merge-v0.3-Q5_K_S.gguf	Q5_K_S	8.459 GB	large, low quality loss - recommended
llama2-merge-v0.3-Q5_K_M.gguf	Q5_K_M	8.699 GB	large, very low quality loss - recommended
llama2-merge-v0.3-Q6_K.gguf	Q6_K	10.058 GB	very large, extremely low quality loss
llama2-merge-v0.3-Q8_0.gguf	Q8_0	13.027 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/llama2-merge-v0.3-GGUF --include "llama2-merge-v0.3-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/llama2-merge-v0.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'