arcee-ai/Trinity-Large-Base

Full fine-tune vs arcee-ai/Trinity-Large-TrueBase. Fine-tune: 100% of the weights changed, across 60 of 60 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 361/361, MLP 2337/2337, Attention 300/300

4 derivatives checked

• arcee-ai/Trinity-Large-Thinking: Full fine-tune
• bartowski/arcee-ai_Trinity-Large-Base-GGUF: Quantization
• arcee-ai/Trinity-Large-Preview: Full fine-tune
• KaoticLord/Trinity-Large-Preview: Full fine-tune

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

On the Hub · Downloads on Model Pulse