Anannta/DeepSeek-R1-STEM-Coder-7B

Full fine-tune vs Anannta/Qwen-STEM-Specialist-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196

2 derivatives checked

• mradermacher/DeepSeek-R1-STEM-Coder-7B-i1-GGUF: Quantization
• mradermacher/DeepSeek-R1-STEM-Coder-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse