aisingapore/Llama-SEA-LION-v3-70B-IT
Full fine-tune vs aisingapore/Llama-SEA-LION-v3-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 160/161, MLP 240/240, Attention 320/320, lm_head 1/1
9 derivatives checked
- mradermacher/llama3.1-70b-cpt-sea-lionv3-instruct-i1-GGUF: Full fine-tune
- aisingapore/Llama-SEA-LION-v3-70B-IT-GGUF: Same weights, converted
- mradermacher/Llama-SEA-LION-v3-70B-IT-i1-GGUF: Quantization
- featherless-ai-quants/aisingapore-llama3.1-70b-cpt-sea-lionv3-instruct-GGUF: Full fine-tune
- aisingapore/Llama-SEA-LION-v3.5-70B-R-GGUF: Full fine-tune
- mradermacher/llama3.1-70b-cpt-sea-lionv3-instruct-GGUF: Full fine-tune
- mradermacher/Llama-SEA-LION-v3-70B-IT-GGUF: Quantization
- tensorblock/aisingapore_Llama-SEA-LION-v3-70B-IT-GGUF: Quantization
- aisingapore/Llama-SEA-LION-v3.5-70B-R: Full fine-tune