tensorblock/Vi-Qwen2-1.5B-RAG-GGUF

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

AITeamVN/Vi-Qwen2-1.5B-RAG - GGUF

This repo contains GGUF format model files for AITeamVN/Vi-Qwen2-1.5B-RAG.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Vi-Qwen2-1.5B-RAG-Q2_K.gguf	Q2_K	0.630 GB	smallest, significant quality loss - not recommended for most purposes
Vi-Qwen2-1.5B-RAG-Q3_K_S.gguf	Q3_K_S	0.709 GB	very small, high quality loss
Vi-Qwen2-1.5B-RAG-Q3_K_M.gguf	Q3_K_M	0.768 GB	very small, high quality loss
Vi-Qwen2-1.5B-RAG-Q3_K_L.gguf	Q3_K_L	0.820 GB	small, substantial quality loss
Vi-Qwen2-1.5B-RAG-Q4_0.gguf	Q4_0	0.871 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Vi-Qwen2-1.5B-RAG-Q4_K_S.gguf	Q4_K_S	0.876 GB	small, greater quality loss
Vi-Qwen2-1.5B-RAG-Q4_K_M.gguf	Q4_K_M	0.918 GB	medium, balanced quality - recommended
Vi-Qwen2-1.5B-RAG-Q5_0.gguf	Q5_0	1.023 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Vi-Qwen2-1.5B-RAG-Q5_K_S.gguf	Q5_K_S	1.023 GB	large, low quality loss - recommended
Vi-Qwen2-1.5B-RAG-Q5_K_M.gguf	Q5_K_M	1.048 GB	large, very low quality loss - recommended
Vi-Qwen2-1.5B-RAG-Q6_K.gguf	Q6_K	1.185 GB	very large, extremely low quality loss
Vi-Qwen2-1.5B-RAG-Q8_0.gguf	Q8_0	1.533 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/Vi-Qwen2-1.5B-RAG-GGUF --include "Vi-Qwen2-1.5B-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/Vi-Qwen2-1.5B-RAG-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'