mergekit-community/nsfw_halp_im_burning_alive_call_911
Full fine-tune (fewer layers) vs mergekit-community/mergekit-model_stock-fpfjlqs. mergekit-community/mergekit-model_stock-fpfjlqs matches part of mergekit-community/nsfw_halp_im_burning_alive_call_911 (291 of its 795 tensors; the rest of mergekit-community/nsfw_halp_im_burning_alive_call_911 has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/nsfw_halp_im_burning_alive_call_911-i1-GGUF: Quantization
- mradermacher/nsfw_halp_im_burning_alive_call_911-GGUF: Quantization