ahmedheakl/asm2asm-qwen-1.5b-100k-float16-attn

Full fine-tune vs Qwen/Qwen2-1.5B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 49/57, MLP 84/84, Attention 196/196

1 derivatives checked

• mradermacher/asm2asm-qwen-1.5b-100k-float16-attn-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse