legraphista/Qwen2-57B-A14B-Instruct-IMat-GGUF

Same weights, converted vs Qwen/Qwen2-57B-A14B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/112, Attention 0/196, Norms 0/57, lm_head 0/1

On the Hub · Downloads on Model Pulse