staeiou/bartleby-qwen3-1.7b_v5

Partial fine-tune vs unsloth/Qwen3-1.7B. Partial change: 82% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 84/113, MLP 84/84, Attention 112/112

1 derivatives checked

• mradermacher/bartleby-qwen3-1.7b_v5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse