Bui1dMySea/LongRAG_Ministral-8B-Instruct

Full fine-tune vs mistralai/Ministral-8B-Instruct-2410. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 4/73, MLP 108/108, Attention 144/144, lm_head 1/1

1 derivatives checked

• mradermacher/LongRAG_Ministral-8B-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse