mradermacher/CantoneseLLM-v2.0-8B-Thinking-Chat-Vector-Merged-GGUF

Same weights, converted vs hon9kon9ize/CantoneseLLM-v2.0-8B-Thinking-Chat-Vector-Merged. Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse