mradermacher/Audar-ASR-V1-Turbo-GGUF

Same weights, converted (fewer layers) vs audarai/Audar-ASR-V1-Turbo. mradermacher/Audar-ASR-V1-Turbo-GGUF matches part of audarai/Audar-ASR-V1-Turbo (311 of its 708 tensors; the rest of audarai/Audar-ASR-V1-Turbo has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse