EVA-UNIT-01/EVA-Qwen2.5-32B-v0.1

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

4 derivatives checked

• bartowski/EVA-Qwen2.5-32B-v0.1-GGUF: Same weights, converted
• mradermacher/EVA-Qwen2.5-32B-v0.1-i1-GGUF: Quantization
• mradermacher/EVA-Qwen2.5-32B-v0.1-GGUF: Quantization
• tensorblock/EVA-Qwen2.5-32B-v0.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse