osunlp/Dreamer-7B-Classifieds

Full fine-tune vs Qwen/Qwen2-VL-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 2/2, Norms 141/187, MLP 215/216, Attention 324/324, lm_head 1/1

1 derivatives checked

• mradermacher/Dreamer-7B-Classifieds-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse