MindIntLab/PsycoLLM

Full fine-tune vs Qwen/Qwen1.5-14B-Chat. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 58/81, MLP 120/120, Attention 280/280, lm_head 1/1

1 derivatives checked

• mradermacher/PsycoLLM-GGUF: Quantization

On the Hub · Downloads on Model Pulse