mradermacher/Mistral-7B-Holodeck-1-Instruct-32k-GGUF

Same weights, converted vs mpasila/Mistral-7B-Holodeck-1-Instruct-32k. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/96, Attention 0/128, Norms 0/65, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse