meta-llama/Llama-3.1-405B-Instruct
Full fine-tune vs meta-llama/Llama-3.1-405B. Fine-tune: 100% of the weights changed, across 126 of 126 layers.
Tensors changed: Embeddings 1/1, Attention 504/504, MLP 378/378, Norms 253/253, lm_head 1/1
15 derivatives checked
- MaziyarPanahi/Meta-Llama-3.1-405B-Instruct-GGUF: Quantization
- nvidia/Llama-3.1-405B-Instruct-FP8: Quantization
- RedHatAI/Meta-Llama-3.1-405B-Instruct-FP8-dynamic: Quantization
- nvidia/Llama-3.1-405B-Instruct-NVFP4: Quantization
- amd/Llama-3.1-405B-Instruct-FP8-KV: Quantization
- amd/Llama-3.1-405B-Instruct-MXFP4-Preview: Quantization
- RedHatAI/Meta-Llama-3.1-405B-Instruct-FP8: Quantization
- meta-llama/Llama-3.1-405B-Instruct-FP8: Quantization
- etemiz/Llama-3.1-405B-Inst-GGUF: Quantization
- nisten/meta-405b-instruct-cpu-optimized-gguf: Same weights, converted
- RedHatAI/Meta-Llama-3.1-405B-Instruct-quantized.w4a16: Quantization
- ApolloRaines/Llama-3.1-405B-Instruct-Jbliterated: LoRA-style
- mlx-community/Llama-3.1-405B-Instruct-8bit: Quantization
- RedHatAI/Meta-Llama-3.1-405B-Instruct-quantized.w8a16: Quantization
- shisa-ai/shisa-v2-llama3.1-405b: Full fine-tune
1 other repos hold byte-for-byte identical weight files.