IDEA-FinAI/TouchstoneGPT-7B-Instruct

Full fine-tune vs Qwen/Qwen2-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1

1 derivatives checked

• mradermacher/TouchstoneGPT-7B-Instruct-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse