Skywork/Skywork-OR1-32B-Preview

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Attention 448/448, MLP 192/192, Norms 127/129, lm_head 1/1

3 derivatives checked

• bartowski/Skywork_Skywork-OR1-32B-Preview-GGUF: Same weights, converted
• mradermacher/Skywork-OR1-32B-Preview-GGUF: Quantization
• lmstudio-community/Skywork-OR1-32B-Preview-GGUF: Quantization

On the Hub · Downloads on Model Pulse