HKUSTAudio/Llasa-1B-Multilingual
Full fine-tune vs meta-llama/Llama-3.2-1B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Norms 33/33, MLP 48/48, Attention 64/64
4 derivatives checked
- OmniAICreator/Galgame-Llasa-1B-v2: Full fine-tune
- OmniAICreator/Galgame-Llasa-1B-v3: Full fine-tune
- OmniAICreator/Galgame-Llasa-1B: Full fine-tune
- GameRuiner/Llasa-1B-Multilingual-Polish: Full fine-tune