TitanML/Qwen2-0.5B-Instruct
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 29/49, MLP 72/72, Attention 168/168
1 derivatives checked
- featherless-ai-quants/TitanML-Qwen2-0.5B-Instruct-GGUF: Quantization
17 other repos hold byte-for-byte identical weight files.