aisingapore/Llama-SEA-LION-v2-8B
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- mradermacher/llama3-8b-cpt-sealionv2-base-i1-GGUF: Quantization
- mradermacher/llama3-8b-cpt-sea-lionv2-base-i1-GGUF: Quantization
- mradermacher/llama3-8b-cpt-sealionv2-base-GGUF: Same weights, converted
- mradermacher/llama3-8b-cpt-sea-lionv2-base-GGUF: Same weights, converted
- featherless-ai-quants/aisingapore-llama3-8b-cpt-sea-lionv2-base-GGUF: Quantization
- mradermacher/Llama-SEA-LION-v2-8B-i1-GGUF: Quantization
- aisingapore/Llama-SEA-LION-v2-8B-IT: Full fine-tune
- mradermacher/Llama-SEA-LION-v2-8B-GGUF: Same weights, converted