allenai/Llama-3.1-Tulu-3-8B
Full fine-tune vs allenai/Llama-3.1-Tulu-3-8B-DPO. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 11/65, MLP 96/96, Attention 128/128, lm_head 1/1
11 derivatives checked
- lmstudio-community/Llama-3.1-Tulu-3-8B-GGUF: Quantization
- bartowski/Llama-3.1-Tulu-3-8B-GGUF: Same weights, converted
- QuantFactory/Tulu-3.1-8B-SuperNova-GGUF: Full fine-tune
- mradermacher/Llama-3.1-Tulu-3-8B-i1-GGUF: Quantization
- mradermacher/Llama-3.1-Tulu-3-8B-GGUF: Same weights, converted
- DevQuasar-7/allenai.Llama-3.1-Tulu-3-8B-GGUF: Same weights, converted
- unsloth/Llama-3.1-Tulu-3-8B-GGUF: Same weights, converted
- QuantFactory/Tulu-MathLingo-8B-GGUF: Full fine-tune
- bunnycore/Tulu-3.1-8B-SuperNova: Full fine-tune
- prithivMLmods/Tulu-MathLingo-8B: LoRA-style
- shisa-ai/ablation-28-rafathenev2.tulu-shisa-v2-tulu3-8b: Full fine-tune
3 other repos hold byte-for-byte identical weight files.