DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1

Full fine-tune vs tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 24/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• mmnga-o/ArrowCanaria-Llama-8B-SFT-v0.1-gguf: Quantization
• DataPilot/ArrowCanaria-Llama-8B-RL-v0.1: LoRA-style

On the Hub · Downloads on Model Pulse