hbx/JustRL-DeepSeek-1.5B

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Attention 196/196, MLP 84/84, Norms 57/57, lm_head 1/1

2 derivatives checked

• mradermacher/JustRL-DeepSeek-1.5B-i1-GGUF: Quantization
• mradermacher/JustRL-DeepSeek-1.5B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse