llm-bg
/

Tucan-2.6B-v1.0-LoRA

function_calling

Model card Files Files and versions

s-emanuilov commited on Jun 8

Commit

604c080

·

verified ·

1 Parent(s): 4911134

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -160,7 +160,7 @@ print(result)
 > 📄 **Full methodology, dataset details, and comprehensive evaluation results coming in the upcoming paper**
-**Dataset:** 2,000+ bilingual (Bulgarian/English) function-calling examples from manual curation + synthetic generation (Gemini/GPT-4).
 **Results:** ~40% improvement in tool-use capabilities over base BgGPT models in internal benchmarks.

 > 📄 **Full methodology, dataset details, and comprehensive evaluation results coming in the upcoming paper**
+**Dataset:** 8,000+ bilingual (Bulgarian/English) function-calling examples across 1,000+ topics, including tool calls with single/multiple arguments, optional parameters, follow-up queries, multi-tool selection, ambiguous queries requiring clarification, and conversational interactions without tool use. Data sourced from manual curation and synthetic generation (Gemini Pro 2.5/GPT-4.1/Sonnet 4).
 **Results:** ~40% improvement in tool-use capabilities over base BgGPT models in internal benchmarks.