reaperdoesntknow/GPT-X2-125M-CIx-Long-Context

Full fine-tune (fewer layers) vs AxiomicLabs/GPT-X2-125M. AxiomicLabs/GPT-X2-125M matches part of reaperdoesntknow/GPT-X2-125M-CIx-Long-Context (332 of its 580 tensors; the rest of reaperdoesntknow/GPT-X2-125M-CIx-Long-Context has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Norms 67/121, Attention 120/120, MLP 90/90, Embeddings 1/1

On the Hub · Downloads on Model Pulse