Downloads · 30 days
45
11% of all-time downloads
colesmcintosh/llama-3.2-3B-gsm8k-q4_k_m-GGUF
llama-3.2-3B-gsm8k-q4_k_m-GGUF is a machine learning model from colesmcintosh. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is the GGUF conversion of the Llama 3.2 3B model fine-tuned using Group Relative Policy Optimization (GRPO) on the GSM8K dataset for improved mathematical reasoning capabilities. The finetuning was performed 2x f…
Downloads · 30 days
45
11% of all-time downloads
All-time downloads
404
Public
Repo size
2 GB
Likes
0
Public
Click a slice to open those files.
.gguf2 GB · 100%
From the Hugging Face model README
This is the GGUF conversion of the Llama 3.2 3B model fine-tuned using Group Relative Policy Optimization (GRPO) on the GSM8K dataset for improved mathematical reasoning capabilities. The finetuning was performed 2x faster with Unsloth and Huggingface's TRL library.
Example usage:
Llama-3.2-3B-GRPO-GSM8K.Q4_K_M.ggufAn Ollama Modelfile is included for easy deployment.