MegaScience/Qwen3-14B-MegaScience

Full fine-tune vs Qwen/Qwen3-14B-Base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 143/161, MLP 120/120, Attention 160/160, lm_head 1/1

3 derivatives checked

• mradermacher/Qwen3-14B-MegaScience-i1-GGUF: Quantization
• mradermacher/Qwen3-14B-MegaScience-GGUF: Quantization
• yamatazen/Qwen3-V-Science-14B: Full fine-tune

On the Hub · Downloads on Model Pulse