mradermacher/aidc-5k-laos-gemma-3-4b-it-v2-GGUF
Same weights, converted (fewer layers) vs Phonepadith/aidc-5k-laos-gemma-3-4b-it-v2. mradermacher/aidc-5k-laos-gemma-3-4b-it-v2-GGUF matches part of Phonepadith/aidc-5k-laos-gemma-3-4b-it-v2 (444 of its 883 tensors; the rest of Phonepadith/aidc-5k-laos-gemma-3-4b-it-v2 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: lm_head 0/1, Norms 0/205, MLP 0/102, Attention 0/136