ModalityDance/latent-tts-coconut

Full fine-tune vs openai-community/gpt2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

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

2 derivatives checked

• jihwan1205/svp-v-coconut-gpt2: Same weights, repacked
• ModalityDance/slpo-coconut-gpt2: Full fine-tune

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

On the Hub · Downloads on Model Pulse