Hugging Face's logo

tensorblock
/
Qwen2-0.5B-ITA-Instruct-GGUF

GGUF
Italian
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Qwen2-0.5B-ITA-Instruct-GGUF / README.md
morriszms's picture
morriszms
Update README.md
f2b0b0e verified
preview code
|
raw
history blame contribute delete
5.01 kB
metadata
license: apache-2.0
datasets:
  - gsarti/clean_mc4_it
  - FreedomIntelligence/alpaca-gpt4-italian
language:
  - it
  - en
base_model: e-palmisano/Qwen2-0.5B-ITA-Instruct
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

e-palmisano/Qwen2-0.5B-ITA-Instruct - GGUF

This repo contains GGUF format model files for e-palmisano/Qwen2-0.5B-ITA-Instruct.

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
Qwen2-0.5B-ITA-Instruct-Q2_K.gguf Q2_K 0.315 GB smallest, significant quality loss - not recommended for most purposes
Qwen2-0.5B-ITA-Instruct-Q3_K_S.gguf Q3_K_S 0.315 GB very small, high quality loss
Qwen2-0.5B-ITA-Instruct-Q3_K_M.gguf Q3_K_M 0.331 GB very small, high quality loss
Qwen2-0.5B-ITA-Instruct-Q3_K_L.gguf Q3_K_L 0.344 GB small, substantial quality loss
Qwen2-0.5B-ITA-Instruct-Q4_0.gguf Q4_0 0.328 GB legacy; small, very high quality loss - prefer using Q3_K_M
Qwen2-0.5B-ITA-Instruct-Q4_K_S.gguf Q4_K_S 0.359 GB small, greater quality loss
Qwen2-0.5B-ITA-Instruct-Q4_K_M.gguf Q4_K_M 0.370 GB medium, balanced quality - recommended
Qwen2-0.5B-ITA-Instruct-Q5_0.gguf Q5_0 0.370 GB legacy; medium, balanced quality - prefer using Q4_K_M
Qwen2-0.5B-ITA-Instruct-Q5_K_S.gguf Q5_K_S 0.384 GB large, low quality loss - recommended
Qwen2-0.5B-ITA-Instruct-Q5_K_M.gguf Q5_K_M 0.391 GB large, very low quality loss - recommended
Qwen2-0.5B-ITA-Instruct-Q6_K.gguf Q6_K 0.471 GB very large, extremely low quality loss
Qwen2-0.5B-ITA-Instruct-Q8_0.gguf Q8_0 0.495 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/Qwen2-0.5B-ITA-Instruct-GGUF --include "Qwen2-0.5B-ITA-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/Qwen2-0.5B-ITA-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'