lemon07r/Qwen3-R1-SLERP-Q3T-8B

Full fine-tune vs Qwen/Qwen3-8B. Fine-tune: 98% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 142/145, MLP 105/108, Attention 140/144, lm_head 1/1

4 derivatives checked

• mradermacher/Qwen3-R1-SLERP-Q3T-8B-i1-GGUF: Quantization
• mradermacher/Qwen3-R1-SLERP-Q3T-8B-GGUF: Same weights, converted
• nbeerbower/Eloisa-Qwen3-8B: LoRA-style
• nbeerbower/Wenyan-Qwen3-8B: LoRA-style

On the Hub · Downloads on Model Pulse