mradermacher/MalayaLLM_Gemma_2_9B_Instruct_V1.0-GGUF

Same weights, converted vs VishnuPJ/MalayaLLM_Gemma_2_9B_Instruct_V1.0. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168

On the Hub · Downloads on Model Pulse