mradermacher/Qwen2.5-VL-7B-Instruct-Unredacted-MAX-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX. mradermacher/Qwen2.5-VL-7B-Instruct-Unredacted-MAX-GGUF matches part of prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX (339 of its 729 tensors; the rest of prithivMLmods/Qwen2.5-VL-7B-Instruct-Unredacted-MAX 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 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse