nasiruddin15/Mistral-grok-instract-2-7B-slerp

Full fine-tune vs HuggingFaceH4/mistral-7b-grok. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

2 derivatives checked

• mradermacher/Mistral-grok-instract-2-7B-slerp-i1-GGUF: Quantization
• mradermacher/Mistral-grok-instract-2-7B-slerp-GGUF: Same weights, converted

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

On the Hub · Downloads on Model Pulse