mradermacher/AksaraLLM-Qwen-1.5B-v5-public-GGUF

Same weights, converted vs AksaraLLM/AksaraLLM-Qwen-1.5B-v5-public. Same weights stored in another dtype (BF16/F32 → F16/F32).

Tensors changed: lm_head 0/1, Norms 0/57, Embeddings 0/1, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse