dphn/Dolphin3.0-Llama3.1-8B
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
20 derivatives checked
- bartowski/Dolphin3.0-Llama3.1-8B-GGUF: Same weights, converted
- itlwas/Dolphin3.0-Llama3.1-8B-Q4_K_M-GGUF: Quantization
- DevQuasar-7/cognitivecomputations.Dolphin3.0-Llama3.1-8B-GGUF: Same weights, converted
- mradermacher/Dolphin3.0-Llama3.1-8B-i1-GGUF: Quantization
- Andycurrent/Dolphin3.0-Llama3.1-8B: Same weights, converted
- mradermacher/Dolphin3.0-Llama3.1-8B-GGUF: Same weights, converted
- h0ney-badger/dolphin-email-8b: LoRA-style
- mlx-community/Dolphin3.0-Llama3.1-8B-MLX-4bit: Quantization
- Mellow5150/Dolphin3.0-Llama3.1-8B-bf16: Same weights, converted
- jmachine/dolphin3-nsfw-gf-chat-gguf: LoRA-style
- mlx-community/Dolphin3.0-Llama3.1-8B-MLX-6bit: Quantization
- mlx-community/Dolphin3.0-Llama3.1-8B-4bit: Quantization
- Parje3t/Dolphin3.0-Llama3.1-8B-Q4_K_M-GGUF: Quantization
- AlSamCur123/NotDolphin3.0-Llama3.1-8: LoRA-style
- skilledu/Dolphin3.0-Llama3.1-8B-abliterated: Abliterated
- h0ney-badger/dolphin3-civic-8b: Quantization
- pki/nova-8b-cybersec: LoRA-style
- AlSamCur123/NotDolphin3.0-Llama3.1-8ContinuedFine: LoRA-style
- Kwoya/Mini-Spyra-v.2.1: Full fine-tune
- Kwoya/Mini-Spyra-v.3.6: Full fine-tune
18 other repos hold byte-for-byte identical weight files.