EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
Partial fine-tune vs Qwen/Qwen2.5-72B. Partial change: 50% of the weights changed (attention, lm_head, mlp), in 80 of 80 layers.
Tensors changed: Embeddings 0/1, MLP 120/240, Attention 280/560, Norms 0/161, lm_head 1/1
9 derivatives checked
- bartowski/EVA-Qwen2.5-72B-v0.1-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-72B-v0.1-i1-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-72B-v0.1-GGUF: Quantization
- KaraKaraWarehouse/SteyrCannon-Qwen2.5-72b: Full fine-tune
- KaraKaraWarehouse/Matsutei-Qwen2.5-72b: Full fine-tune
- KaraKaraWarehouse/EurobeatVARemix-Qwen2.5-72b: Full fine-tune
- sophosympatheia/Evathene-v1.0: Full fine-tune
- SteelStorage/Q2.5-MS-Mistoria-72b: Full fine-tune
- chakchouk/BBA-ECE-TRIOMPHANT-Qwen2.5-72B: Full fine-tune