mradermacher/InftyThink-Plus-T-4B-GGUF

Same weights, converted vs yanyc/InftyThink-Plus-T-4B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/108, Norms 0/145, Attention 0/144

On the Hub · Downloads on Model Pulse