EVA-UNIT-01/EVA-Qwen2.5-7B-v0.0
Partial fine-tune vs Qwen/Qwen2.5-7B. Partial change: 50% of the weights changed (attention, lm_head, mlp), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 42/84, Attention 98/196, lm_head 1/1
4 derivatives checked
- mradermacher/EVA-Qwen2.5-7B-v0.0-i1-GGUF: Quantization
- bartowski/EVA-Qwen2.5-7B-v0.0-GGUF: Same weights, converted
- mradermacher/EVA-Qwen2.5-7B-v0.0-GGUF: Same weights, converted
- bunnycore/Qwen2.5-7B-HyperMix: Full fine-tune