meta-llama/Llama-3.1-8B-Instruct
Full fine-tune vs meta-llama/Llama-3.1-8B. 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
634 derivatives checked
- bartowski/Meta-Llama-3.1-8B-Instruct-GGUF: Quantization
- unsloth/Meta-Llama-3.1-8B-Instruct: Identical copy
- unsloth/Llama-3.1-8B-Instruct: Identical copy
- MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF: Quantization
- RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8: Quantization
- Skywork/Skywork-Reward-Llama-3.1-8B-v0.2: Full fine-tune
- GaleneAI/llama-3.1-nemoguard-8b-content-safety-merged-NVFP4: Quantization
- lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF: Quantization
- unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit: Quantization
- nvidia/Llama-3.1-8B-Instruct-FP8: Quantization
- nvidia/Llama-3.1-8B-Instruct-NVFP4: Quantization
- RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w4a16: Quantization
- westlake-repl/Evolla-10B-hf: Full fine-tune (fewer layers)
- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF: Abliterated
- unsloth/Meta-Llama-3.1-8B-Instruct-unsloth-bnb-4bit: Quantization
- RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8-dynamic: Quantization
- mlx-community/Llama-3.1-8B-Instruct-4bit: Quantization
- unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit: Quantization
- unsloth/Llama-3.1-8B-Instruct-GGUF: Same weights, converted
- RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8: Quantization
- Skywork/Skywork-Reward-V2-Llama-3.1-8B: Full fine-tune
- unsloth/meta-Llama-3.1-8B-unsloth-bnb-4bit: Quantization
- CNCL-Penn-State/CrPO-sft-llama-3.1-8b-instruct: LoRA-style
- Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3: Full fine-tune
- Team-ACE/ToolACE-8B: LoRA-style
- modularai/Llama-3.1-8B-Instruct-GGUF: Same weights, converted
- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated: Abliterated
- shenzhi-wang/Llama3.1-8B-Chinese-Chat: Full fine-tune
- RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3: Full fine-tune
- pearl-ai/Llama-3.1-8B-Instruct-pearl: Quantization
161 other repos hold byte-for-byte identical weight files.