tokyotech-llm/Llama-3.1-Swallow-8B-v0.5
Full fine-tune vs meta-llama/Llama-3.1-8B-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
5 derivatives checked
- tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5: Full fine-tune
- mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF: Quantization
- mradermacher/Llama-3.1-Swallow-8B-v0.5-GGUF: Same weights, converted
- neody/Llama-3.1-Swallow-8B-v0.5-gguf: Same weights, converted
- mpasila/Llama-3.1-Swallow-JP-EN-Translator-v1-8B: LoRA-style