mradermacher/Qwen1.5-7B-Dutch-Chat-Sft-Bf16-GGUF

Same weights, converted vs robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/224, lm_head 0/1

On the Hub · Downloads on Model Pulse