Timegravity/tamil-lm-2b-instruct
Partial fine-tune vs Qwen/Qwen3.5-2B-Base. Partial change: 83% of the weights changed (attention, embeddings, mlp, norms, other), in 24 of 24 layers.
Tensors changed: Attention 82/268, Norms 8/183, MLP 79/175, Embeddings 2/4, other 1/1
1 derivatives checked
- mradermacher/tamil-lm-2b-instruct-GGUF: Same weights, converted