tensorblock/Llama3-ChatQA-1.5-8B-GGUF

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

nvidia/Llama3-ChatQA-1.5-8B - GGUF

This repo contains GGUF format model files for nvidia/Llama3-ChatQA-1.5-8B.

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

<|begin_of_text|>System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.

User: {prompt}

Assistant:

Model file specification

Filename	Quant type	File Size	Description
Llama3-ChatQA-1.5-8B-Q2_K.gguf	Q2_K	2.961 GB	smallest, significant quality loss - not recommended for most purposes
Llama3-ChatQA-1.5-8B-Q3_K_S.gguf	Q3_K_S	3.413 GB	very small, high quality loss
Llama3-ChatQA-1.5-8B-Q3_K_M.gguf	Q3_K_M	3.743 GB	very small, high quality loss
Llama3-ChatQA-1.5-8B-Q3_K_L.gguf	Q3_K_L	4.025 GB	small, substantial quality loss
Llama3-ChatQA-1.5-8B-Q4_0.gguf	Q4_0	4.341 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama3-ChatQA-1.5-8B-Q4_K_S.gguf	Q4_K_S	4.370 GB	small, greater quality loss
Llama3-ChatQA-1.5-8B-Q4_K_M.gguf	Q4_K_M	4.583 GB	medium, balanced quality - recommended
Llama3-ChatQA-1.5-8B-Q5_0.gguf	Q5_0	5.215 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama3-ChatQA-1.5-8B-Q5_K_S.gguf	Q5_K_S	5.215 GB	large, low quality loss - recommended
Llama3-ChatQA-1.5-8B-Q5_K_M.gguf	Q5_K_M	5.339 GB	large, very low quality loss - recommended
Llama3-ChatQA-1.5-8B-Q6_K.gguf	Q6_K	6.143 GB	very large, extremely low quality loss
Llama3-ChatQA-1.5-8B-Q8_0.gguf	Q8_0	7.954 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/Llama3-ChatQA-1.5-8B-GGUF --include "Llama3-ChatQA-1.5-8B-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/Llama3-ChatQA-1.5-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'