aisingapore/Llama-SEA-LION-v2-8B-IT
Full fine-tune vs aisingapore/Llama-SEA-LION-v2-8B. 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
14 derivatives checked
- mradermacher/llama3-8b-cpt-sea-lionv2-instruct-GGUF: Full fine-tune
- mradermacher/llama3-8b-cpt-sea-lionv2-instruct-i1-GGUF: Full fine-tune
- mradermacher/llama3-8b-cpt-sealionv2-instruct-i1-GGUF: Full fine-tune
- mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF: Full fine-tune
- mradermacher/llama3-8b-cpt-sea-lionv2.1-instruct-i1-GGUF: Quantization
- mradermacher/Llama-SEA-LION-v2-8B-IT-i1-GGUF: Quantization
- aisingapore/Llama-SEA-LION-v2-8B-IT-GGUF: Quantization
- featherless-ai-quants/aisingapore-llama3-8b-cpt-sea-lionv2-instruct-GGUF: Quantization
- featherless-ai-quants/aisingapore-llama3-8b-cpt-sea-lionv2.1-instruct-GGUF: Quantization
- mradermacher/Llama-SEA-LION-v2-8B-IT-GGUF: Same weights, converted
- mradermacher/llama3-8b-cpt-sea-lionv2.1-instruct-GGUF: Same weights, converted
- tensorblock/aisingapore_Llama-SEA-LION-v2-8B-IT-GGUF: Quantization
- GoToCompany/llama3-8b-cpt-sahabatai-v1-base: Full fine-tune
- govtech/llama3-8b-sea-lionv2.1-instruct-secure: LoRA-style