tensorblock/SeaLLM-7B-v2.5-GGUF

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

SeaLLMs/SeaLLM-7B-v2.5 - GGUF

This repo contains GGUF format model files for SeaLLMs/SeaLLM-7B-v2.5.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

<bos><|im_start|>system
{system_prompt}<eos>
<|im_start|>user
{prompt}<eos>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
SeaLLM-7B-v2.5-Q2_K.gguf	Q2_K	3.242 GB	smallest, significant quality loss - not recommended for most purposes
SeaLLM-7B-v2.5-Q3_K_S.gguf	Q3_K_S	3.709 GB	very small, high quality loss
SeaLLM-7B-v2.5-Q3_K_M.gguf	Q3_K_M	4.069 GB	very small, high quality loss
SeaLLM-7B-v2.5-Q3_K_L.gguf	Q3_K_L	4.386 GB	small, substantial quality loss
SeaLLM-7B-v2.5-Q4_0.gguf	Q4_0	4.668 GB	legacy; small, very high quality loss - prefer using Q3_K_M
SeaLLM-7B-v2.5-Q4_K_S.gguf	Q4_K_S	4.700 GB	small, greater quality loss
SeaLLM-7B-v2.5-Q4_K_M.gguf	Q4_K_M	4.964 GB	medium, balanced quality - recommended
SeaLLM-7B-v2.5-Q5_0.gguf	Q5_0	5.570 GB	legacy; medium, balanced quality - prefer using Q4_K_M
SeaLLM-7B-v2.5-Q5_K_S.gguf	Q5_K_S	5.570 GB	large, low quality loss - recommended
SeaLLM-7B-v2.5-Q5_K_M.gguf	Q5_K_M	5.723 GB	large, very low quality loss - recommended
SeaLLM-7B-v2.5-Q6_K.gguf	Q6_K	6.529 GB	very large, extremely low quality loss
SeaLLM-7B-v2.5-Q8_0.gguf	Q8_0	8.454 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/SeaLLM-7B-v2.5-GGUF --include "SeaLLM-7B-v2.5-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/SeaLLM-7B-v2.5-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'