RISys-Lab/RedSage-Qwen3-8B-Base

Full fine-tune vs RISys-Lab/RedSage-Qwen3-8B-CFW. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 139/145, MLP 108/108, Attention 144/144, lm_head 1/1

4 derivatives checked

• mradermacher/RedSage-Qwen3-8B-Base-i1-GGUF: Quantization
• RISys-Lab/RedSage-Qwen3-8B-Ins: Full fine-tune
• mradermacher/RedSage-Qwen3-8B-Base-GGUF: Same weights, converted
• LinHekaka/RedSage-Qwen3-8B-Ins: Full fine-tune

On the Hub · Downloads on Model Pulse