11-47/Distil-Grok4.4-Minute.Codex.NSFW-0.1B
Full fine-tune vs distilbert/distilgpt2. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Attention 24/24, Norms 26/26, MLP 24/24, Embeddings 2/2
1 derivatives checked
- mradermacher/Distil-Grok4.4-Minute.Codex.NSFW-0.1B-GGUF: Same weights, converted