mergekit-community/nsfw_ts_too_late_im_burnt_to_a_crisp
Partial fine-tune (fewer layers) vs mergekit-community/nsfw_merge_test_vFFS. mergekit-community/nsfw_merge_test_vFFS matches part of mergekit-community/nsfw_ts_too_late_im_burnt_to_a_crisp (291 of its 579 tensors; the rest of mergekit-community/nsfw_ts_too_late_im_burnt_to_a_crisp has no counterpart). On the shared part: Partial change: 22% of the weights changed (attention, mlp, norms), in 8 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 16/65, MLP 24/96, Attention 32/128
2 derivatives checked
- mradermacher/nsfw_ts_too_late_im_burnt_to_a_crisp-i1-GGUF: Quantization
- mradermacher/nsfw_ts_too_late_im_burnt_to_a_crisp-GGUF: Quantization