markab/Qwen1.5-Capybara-0.5B-Chat

Partial fine-tune vs Qwen/Qwen1.5-0.5B-Chat. Partial change: 19% of the weights changed (attention, mlp), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 11/72, Attention 58/168

1 derivatives checked

• mradermacher/Qwen1.5-Capybara-0.5B-Chat-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse