EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
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
12 derivatives checked
- bartowski/EVA-Qwen2.5-72B-v0.2-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-72B-v0.2-i1-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-72B-v0.2-GGUF: Quantization
- sophosympatheia/Evathene-v1.2: Full fine-tune
- sophosympatheia/Evathene-v1.1: Full fine-tune
- nbeerbower/EVA-abliterated-TIES-Qwen2.5-72B: Full fine-tune
- DatToad/Chuluun-Qwen2.5-72B-v0.08: Full fine-tune
- maldv/Eva-Mindlink-72b: Full fine-tune
- DatToad/Chuluun-Qwen2.5-72B-v0.01: Full fine-tune
- SteelStorage/Q2.5-MS-Mistoria-72b-v2: Full fine-tune
- TareksGraveyard/Savant-Qwen2.5-72B: Full fine-tune
- TareksGraveyard/Thespian-Qwen2.5-72B: Full fine-tune