meditsolutions/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune

Same weights, repacked vs meditsolutions/MSH-v1-Bielik-v2.3-Instruct-MedIT-merge. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Norms 0/101, Attention 0/200, lm_head 0/1

1 derivatives checked

• mradermacher/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse