bartowski/BigQwen2.5-Echo-47B-Instruct-GGUF

Same weights, converted vs mlabonne/BigQwen2.5-Echo-47B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/189, MLP 0/282, Attention 0/658

On the Hub · Downloads on Model Pulse