EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
Partial fine-tune vs Qwen/Qwen2.5-32B. Partial change: 50% of the weights changed (attention, lm_head, mlp), in 63 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 96/192, Attention 224/448, lm_head 1/1
21 derivatives checked
- bartowski/EVA-Qwen2.5-32B-v0.2-GGUF: Same weights, converted
- backyardai/EVA-Qwen2.5-32B-v0.2-GGUF: Same weights, converted
- mradermacher/EVA-Qwen2.5-32B-v0.2-i1-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-32B-v0.2-GGUF: Quantization
- thaddeusk/EVA-Qwen2.5-32B-v0.2-AWQ-Int4: Quantization
- nbeerbower/EVA-Gutenberg3-Qwen2.5-32B: Same weights, repacked
- nbeerbower/EVA-Rombos1-Qwen2.5-32B: Full fine-tune
- nitky/RoguePlanet-DeepSeek-R1-Qwen-32B-RP: Full fine-tune
- nbeerbower/Azura-Qwen2.5-32B: Full fine-tune
- win10/EVA-QwQ-32B-Preview: Partial fine-tune
- jackboot/uwu-qwen-32b: Full fine-tune
- maldv/Loqwqtus2.5-32B-Instruct: Full fine-tune
- win10/EVA-QwQ-32B-Coder-Preview: Full fine-tune
- BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-4x-TIES-MGS-v1.0: Full fine-tune
- BenevolenceMessiah/QwQ-32B-Preview-Self-instruct-3x-TIES-v1.0: Full fine-tune
- estrogen/UwU-1: Full fine-tune
- ParasiticRogue/EVA-Instruct-SP-32B: Full fine-tune
- BenevolenceMessiah/QwQ-32B-Preview-abliterated-Self-instruct-3x-TIES-v1.0: Full fine-tune
- BenevolenceMessiah/QwQ-32B-Preview-Self-instruct-4x-TIES-MGS-v1.0: Full fine-tune
- marcuscedricridia/Springer-32B-RP-4: Partial fine-tune
- ParasiticRogue/EVA-Instruct-32B-v2: Full fine-tune
3 other repos hold byte-for-byte identical weight files.