Sao10K/Llama-3.3-70B-Vulpecula-r1
Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. 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
10 derivatives checked
- bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF: Quantization
- mradermacher/Llama-3.3-70B-Vulpecula-r1-i1-GGUF: Quantization
- mradermacher/Llama-3.3-70B-Vulpecula-r1-GGUF: Quantization
- sophosympatheia/Electranova-70B-v1.0: Full fine-tune
- Delta-Vector/Austral-70B-Preview: LoRA-style
- TareksLab/DarkThoughts-LLaMa-70B: Full fine-tune
- Mawdistical/Squelching-Fantasies-70B-Regent: Full fine-tune
- ddh0/Andromeda-70B: Full fine-tune
- Nexesenex/Llama_3.x_70b_L3.3_VulpeculHiggs_128K_v1.02: Partial fine-tune
- cloe2302/Llama-3.3-70B-Vulpecula-r1-Negative: Full fine-tune