marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.4-1M

Full fine-tune vs Qwen/Qwen2.5-7B-Instruct-1M. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196

3 derivatives checked

• mradermacher/Hush-Qwen2.5-7B-RP-v1.4-1M-i1-GGUF: Quantization
• MaziyarPanahi/Hush-Qwen2.5-7B-RP-v1.4-1M-GGUF: Same weights, converted
• marcuscedricridia/Hush-Qwen2.5-7B-v1.4: Full fine-tune

On the Hub · Downloads on Model Pulse