mradermacher/Qwen3-ASR-1.7B-Uncensored-GGUF

Same weights, converted (fewer layers) vs freeuser17/Qwen3-ASR-1.7B-Uncensored. mradermacher/Qwen3-ASR-1.7B-Uncensored-GGUF matches part of freeuser17/Qwen3-ASR-1.7B-Uncensored (311 of its 708 tensors; the rest of freeuser17/Qwen3-ASR-1.7B-Uncensored 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