Team-ACE/EnvACE-Qwen3-1.7B

Partial fine-tune vs Qwen/Qwen3-1.7B. Partial change: 69% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 90/113, MLP 84/84, Attention 112/112, lm_head 0/1

2 derivatives checked

• mradermacher/EnvACE-Qwen3-1.7B-i1-GGUF: Quantization
• mradermacher/EnvACE-Qwen3-1.7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse