LSXPrime/ProseFlow-v1-360M-Instruct

Full fine-tune vs HuggingFaceTB/SmolLM-360M-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/ProseFlow-v1-360M-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse