THU-KEG/LongWriter-V-7B-DPO

Partial fine-tune vs THU-KEG/LongWriter-V-7B. Partial change: 85% of the weights changed (attention, lm_head, mlp, norms), in 28 of 32 layers.

Tensors changed: Embeddings 0/2, Norms 53/122, MLP 84/280, Attention 196/324, lm_head 1/1

2 derivatives checked

• mradermacher/LongWriter-V-7B-DPO-i1-GGUF: Quantization (fewer layers)
• mradermacher/LongWriter-V-7B-DPO-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse