Downloads · 30 days
4
7% of all-time downloads
jan-hq/AlphaMaze-v0.2-1.5B-GRPO-cp-250
AlphaMaze-v0.2-1.5B-GRPO-cp-250 is a text generation model from jan-hq. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: jan-hq - License: apache-2.0 - Finetuned from model : jan-hq/AlphaMaze-v0.1-1.5B-GRPO-cp-600
Downloads · 30 days
4
7% of all-time downloads
All-time downloads
58
Public
Parameters
1.8B
3.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.6 GB · 100%
From the Hugging Face model README
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.