Downloads · 30 days
37
18% of all-time downloads
x1nx3r/Llama-3.2-3B-thinking-v3-13.9K-GGUF
Llama-3.2-3B-thinking-v3-13.9K-GGUF is a machine learning model from x1nx3r. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This folder contains a float16 GGUF export of the outputsft fine-tuned Llama-3.2-3B-Instruct model along with the tokenizer assets required for Hugging Face uploads.
Downloads · 30 days
37
18% of all-time downloads
All-time downloads
205
Public
Repo size
6.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf6.4 GB · 100%
From the Hugging Face model README
This folder contains a float16 GGUF export of the output_sft fine-tuned Llama-3.2-3B-Instruct model along with the tokenizer assets required for Hugging Face uploads.
output_sft-f16.gguf – converted weights (float16)config.json – original Hugging Face config for referencetokenizer.json, tokenizer_config.json, special_tokens_map.json, generation_config.json – tokenizer and generation settings./llama-b7083-bin-ubuntu-x64/bin/llama-cli \
-m output_sft-f16.gguf \
-p "Hello, world!"
When uploading to Hugging Face, include these files and add a model card describing the fine-tuning data and license.