mradermacher/VamMed1.0-4B-GGUF

Same weights, converted (fewer layers) vs vamcrizer/VamMed1.0-4B. mradermacher/VamMed1.0-4B-GGUF matches part of vamcrizer/VamMed1.0-4B (444 of its 883 tensors; the rest of vamcrizer/VamMed1.0-4B has no counterpart). On the shared part: Same weights stored in another dtype (F16/BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse