mergekit-community/Qwen2-2B-RepleteCoder-DHM

Full fine-tune vs mergekit-community/Qwen2-2B-Dolphin-Hercules. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/73, MLP 108/108, Attention 252/252

1 derivatives checked

• mradermacher/Qwen2-2B-RepleteCoder-DHM-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse