mradermacher/TheTop-5x7B-Instruct-S3-v0.1-GGUF

Same weights, converted vs MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1. Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse