katanemo/Arch-Agent-32B

Full fine-tune vs Qwen/Qwen2.5-Coder-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/Arch-Agent-32B-i1-GGUF: Quantization
• mradermacher/Arch-Agent-32B-GGUF: Quantization
• DevQuasar/katanemo.Arch-Agent-32B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse