BanglaLLM/BanglaLLama-3.2-3b-bangla-alpaca-orca-instruct-v0.0.1

Partial fine-tune vs BanglaLLM/BanglaLLama-3.2-3b-unlop-culturax-base-v0.0.3. Partial change: 89% of the weights changed (attention, lm_head, mlp), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/112, lm_head 1/1

1 derivatives checked

• mradermacher/BanglaLLama-3.2-3b-bangla-alpaca-orca-instruct-v0.0.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse