unsloth/Qwen2.5-72B

Same weights, repacked vs Qwen/Qwen2.5-72B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1

1 derivatives checked

• featherless-ai-quants/unsloth-Qwen2.5-72B-GGUF: Quantization

On the Hub · Downloads on Model Pulse