McGill-NLP/delethink-96k-1.5b

Partial fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Attention 196/196, MLP 84/84, Norms 43/57, lm_head 0/1

2 derivatives checked

• mradermacher/delethink-96k-1.5b-i1-GGUF: Quantization
• mradermacher/delethink-96k-1.5b-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse