simonko912/SimonGPT-simple-instruct

Full fine-tune vs openai-community/gpt2. Fine-tune: 99% of the weights changed, across 12 of 12 layers.

Tensors changed: Norms 50/50, Attention 48/48, MLP 48/48, Embeddings 1/2

2 derivatives checked

• mradermacher/SimonGPT-simple-instruct-i1-GGUF: Quantization
• mradermacher/SimonGPT-simple-instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse