meta-llama/Llama-3.1-70B-Instruct
Full fine-tune vs meta-llama/Llama-3.1-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
58 derivatives checked
- RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8: Quantization
- MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- bartowski/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF: Full fine-tune
- lmstudio-community/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16: Quantization
- unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit: Quantization
- nvidia/Llama-3.1-70B-Instruct-FP8: Quantization
- unsloth/Meta-Llama-3.1-70B-Instruct: Identical copy
- legraphista/Meta-Llama-3.1-70B-Instruct-IMat-GGUF: Same weights, converted
- amd/Llama-3.1-70B-Instruct-FP8-KV: Quantization
- qwp4w3hyb/Meta-Llama-3.1-70B-Instruct-iMat-GGUF: Same weights, converted
- mradermacher/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- backyardai/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- mradermacher/Meta-Llama-3.1-70B-Instruct-i1-GGUF: Quantization
- MarsupialAI/Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF: Full fine-tune
- HiTZ/Latxa-Llama-3.1-70B-Instruct: Full fine-tune
- second-state/Meta-Llama-3.1-70B-Instruct-GGUF: Same weights, converted
- c4tdr0ut/grok-oss-Revenant-70B: Full fine-tune
- shenzhi-wang/Llama3.1-70B-Chinese-Chat: Full fine-tune
- mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF: Quantization
- mattshumer/Reflection-Llama-3.1-70B: Full fine-tune
- RedHatAI/Llama-3.1-70B-Instruct-NVFP4: Quantization
- gaianet/Meta-Llama-3.1-70B-Instruct-GGUF: Same weights, converted
- SicariusSicariiStuff/Assistant_Pepe_70B: Full fine-tune
- RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8: Quantization
- RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic: Quantization
- DevQuasar-4/Meta-Llama-3.1-70B-Instruct-GGUF: Quantization
- mlabonne/Llama-3.1-70B-Instruct-lorablated: Partial fine-tune
- mlx-community/Meta-Llama-3.1-70B-Instruct-bf16: Same weights, repacked
10 other repos hold byte-for-byte identical weight files.