✅ Outperforms GPT-4o & other top domain-specific models on:
📌 MultiWOZ 2.4 (TOD)
📌 BFCL V3 (Function Calling)
📌 API-Bank (Function Calling)
Achieving top zero-shot scores not in one but across all benchmarks!
✅ Outperforms GPT-4o & other top domain-specific models on:
📌 MultiWOZ 2.4 (TOD)
📌 BFCL V3 (Function Calling)
📌 API-Bank (Function Calling)
Achieving top zero-shot scores not in one but across all benchmarks!
📊 Models: CALM 8B, CALM 70B, CALM-405B trained from Llama model series
📊 Models: CALM 8B, CALM 70B, CALM-405B trained from Llama model series
Introducing CALM, fully open-source Conversational Agentic Language Models with CALM 8B, CALM 70B, and CALM 405B-excelling in both multi-turn dialogue management & function calling.
🌐Project Page: emrecanacikgoz.github.io/CALM/
Introducing CALM, fully open-source Conversational Agentic Language Models with CALM 8B, CALM 70B, and CALM 405B-excelling in both multi-turn dialogue management & function calling.
🌐Project Page: emrecanacikgoz.github.io/CALM/