AI4SGI/ExoMind

Full fine-tune vs Qwen/Qwen3.5-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.

Tensors changed: MLP 280/1165, lm_head 1/1, Embeddings 1/5, Attention 233/392, other 0/1, Norms 93/247

3 derivatives checked

• mradermacher/ExoMind-GGUF: Quantization
• mradermacher/ExoMind-i1-GGUF: Quantization
• AI4SGI/ExoMind-Q8_0-GGUF: Quantization

On the Hub · Downloads on Model Pulse