OBLITERATUS/gpt2-xl-OBLITERATED

Partial fine-tune vs openai-community/gpt2-xl. Partial change: 17% of the weights changed (attention, embeddings, mlp), in 9 of 48 layers.

Tensors changed: Attention 27/192, Norms 0/194, MLP 18/192, Embeddings 1/2

2 derivatives checked

• mradermacher/gpt2-xl-OBLITERATED-i1-GGUF: Quantization
• mradermacher/gpt2-xl-OBLITERATED-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse