EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1
Partial fine-tune vs Qwen/Qwen2.5-14B. Partial change: 50% of the weights changed (attention, lm_head, mlp), in 45 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 72/144, Attention 168/336, lm_head 1/1
6 derivatives checked
- mradermacher/EVA-Qwen2.5-14B-v0.1-i1-GGUF: Quantization
- mradermacher/EVA-Qwen2.5-14B-v0.1-GGUF: Quantization
- bartowski/EVA-Qwen2.5-14B-v0.1-GGUF: Same weights, converted
- QuantFactory/Celestial-Harmony-14b-v1.0-Experimental-1016-GGUF: Full fine-tune
- LyraNovaHeart/Celestial-Harmony-14b-v1.0-Experimental-1016: Full fine-tune
- LyraNovaHeart/Celestial-Harmony-14b-v1.0-Experimental-1015: Full fine-tune