EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
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
13 derivatives checked
- bartowski/EVA-Qwen2.5-14B-v0.2-GGUF: Same weights, converted
- mradermacher/EVA-Qwen2.5-14B-v0.2-i1-GGUF: Quantization
- QuantFactory/Q2.5-Veltha-14B-GGUF: Full fine-tune
- QuantFactory/Q2.5-Veltha-14B-0.5-GGUF: Full fine-tune
- mradermacher/EVA-Qwen2.5-14B-v0.2-GGUF: Quantization
- sometimesanotion/Qwen2.5-14B-Vimarckoso-v3: Full fine-tune
- djuna/Q2.5-Veltha-14B-0.5: Full fine-tune
- nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B: Full fine-tune
- djuna/Q2.5-Veltha-14B: Full fine-tune
- sometimesanotion/Qwenvergence-14B-v12-Prose-DS: Full fine-tune
- win10/SphinxMind-14B-normalize-false: Full fine-tune
- win10/EVA-Meissa-Coder-14B-Instruct: Full fine-tune
- win10/SphinxMind-14B: Full fine-tune