πŸ‡§πŸ‡© Polymath-1.5B-Bengali-Math

This model is a merge of Qwen/Qwen2.5-1.5B and Qwen/Qwen2.5-1.5B-Instruct created using the SLERP method.

πŸ§ͺ Research Goal

To investigate the "Capacity Gap" in low-resource languages (like Bengali) when transferring mathematical reasoning capabilities without fine-tuning.

πŸ“Š Performance

  • English Math Logic: 60% Accuracy (Retained Logic) βœ…
  • Bengali Math Logic: 0% Accuracy (Capacity Constraint Revealed) ⚠️

πŸ› οΈ Method

Merged using MergeKit with the following config:

  • Method: SLERP
  • Precision: float16
  • Parameters: 1.5 Billion

Created for research and educational purposes.

Downloads last month
-
Safetensors
Model size
2B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Noushad999/Polymath-1.5B-Bengali-Math

Merge model
this model
Quantizations
1 model