Uploaded model

  • Developed by: jan-hq
  • License: apache-2.0
  • Finetuned from model : jan-hq/Deepseek-Qwen2.5-7B-Redistil

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
8
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jan-hq/Deepseek-Qwen2.5-7B-Redistil-GRPO

Finetuned
(2)
this model
Quantizations
1 model