aisingapore/Llama-SEA-LION-v3-70B
Full fine-tune vs meta-llama/Llama-3.1-70B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 84/161, MLP 240/240, Attention 320/320, lm_head 1/1
5 derivatives checked
- mradermacher/Llama-SEA-LION-v3-70B-i1-GGUF: Quantization
- mradermacher/llama3.1-70b-cpt-sea-lionv3-base-i1-GGUF: Quantization
- mradermacher/Llama-SEA-LION-v3-70B-GGUF: Quantization
- mradermacher/llama3.1-70b-cpt-sea-lionv3-base-GGUF: Quantization
- aisingapore/Llama-SEA-LION-v3-70B-IT: Full fine-tune