vllm-sr/Decision-2.0-Eos-0.8B

Full fine-tune vs vllm-sr/Decision-1.0-Eos-0.8B. Fine-tune: 100% of the weights changed, across 0 of 0 layers.

Tensors changed: MLP 3/3, Norms 4/4, other 3/3

2 derivatives checked

• vllm-sr/Vela-2.0-0.8B: Full fine-tune (fewer layers)
• vllm-sr/Decision-2.0-Eos-0.8B-GGUF: Same weights, repacked (fewer layers)

On the Hub · Downloads on Model Pulse