tensorblock/Vikhr-Llama-3.2-1B-Instruct-GGUF

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

Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct - GGUF

This repo contains GGUF format model files for Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct.

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|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 12 Nov 2024

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
Vikhr-Llama-3.2-1B-Instruct-Q2_K.gguf	Q2_K	0.541 GB	smallest, significant quality loss - not recommended for most purposes
Vikhr-Llama-3.2-1B-Instruct-Q3_K_S.gguf	Q3_K_S	0.598 GB	very small, high quality loss
Vikhr-Llama-3.2-1B-Instruct-Q3_K_M.gguf	Q3_K_M	0.643 GB	very small, high quality loss
Vikhr-Llama-3.2-1B-Instruct-Q3_K_L.gguf	Q3_K_L	0.682 GB	small, substantial quality loss
Vikhr-Llama-3.2-1B-Instruct-Q4_0.gguf	Q4_0	0.718 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Vikhr-Llama-3.2-1B-Instruct-Q4_K_S.gguf	Q4_K_S	0.722 GB	small, greater quality loss
Vikhr-Llama-3.2-1B-Instruct-Q4_K_M.gguf	Q4_K_M	0.752 GB	medium, balanced quality - recommended
Vikhr-Llama-3.2-1B-Instruct-Q5_0.gguf	Q5_0	0.831 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Vikhr-Llama-3.2-1B-Instruct-Q5_K_S.gguf	Q5_K_S	0.831 GB	large, low quality loss - recommended
Vikhr-Llama-3.2-1B-Instruct-Q5_K_M.gguf	Q5_K_M	0.849 GB	large, very low quality loss - recommended
Vikhr-Llama-3.2-1B-Instruct-Q6_K.gguf	Q6_K	0.952 GB	very large, extremely low quality loss
Vikhr-Llama-3.2-1B-Instruct-Q8_0.gguf	Q8_0	1.230 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/Vikhr-Llama-3.2-1B-Instruct-GGUF --include "Vikhr-Llama-3.2-1B-Instruct-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/Vikhr-Llama-3.2-1B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'