ncgc/pythia-2.8b-sft

Full fine-tune vs EleutherAI/pythia-2.8b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 2/2, Norms 102/130, Attention 128/128, MLP 128/128

2 derivatives checked

• mradermacher/pythia-2.8b-sft-i1-GGUF: Quantization
• mradermacher/pythia-2.8b-sft-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse