prince-canuma/Ministral-8B-Instruct-2410-HF

Same weights, converted vs mistralai/Ministral-8B-Instruct-2410. Same weights stored in another dtype (BF16 → F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144, lm_head 0/1

1 derivatives checked

• bartowski/Ministral-8B-Instruct-2410-HF-GGUF-TEST: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse