Safetensors
English
llama
emrecanacikgoz commited on
Commit
e2e9cd4
·
verified ·
1 Parent(s): a5c4043

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -10
README.md CHANGED
@@ -21,12 +21,13 @@ base_model:
21
 
22
  CALM-8B is trained on a **multi-task dataset** covering dialogue state tracking, function calling, and multi-turn reasoning. The model outperforms top proprietary and domain-specific models, including **GPT-4o**, on key evaluation benchmarks: **MultiWOZ 2.4 (TOD), BFCL V3 (LA), and API-Bank (LA).**
23
 
24
- ## Model Sources [TODO]
25
 
26
  <!-- Provide the basic links for the model. -->
27
 
28
- - **Paper [optional]:** [More Information Needed]
29
- - **Repository:** [More Information Needed]
 
30
 
31
 
32
 
@@ -35,7 +36,7 @@ CALM-8B is trained on a **multi-task dataset** covering dialogue state tracking,
35
 
36
  - **Model Name:** CALM-8B
37
  - **Developed by:** Colloboration of UIUC Conversational AI LAB and Oumi
38
- - **License:** Apache 2.0
39
  - **Architecture:** Fine-tuned **Llama 3.1 8B Instruct**
40
  - **Training Data:** CALM-IT dataset
41
  - **Fine-tuning Framework:** [Oumi](https://github.com/oumi-ai/oumi)
@@ -117,13 +118,16 @@ This model is licensed under [Creative Commons NonCommercial (CC BY-NC 4.0)](htt
117
  ## Citation
118
  If you use **CALM-8B** in your research, please cite:
119
  ```
120
- @article{yourpaper2024,
121
- title={CALM: Conversational Agentic Language Model},
122
- author={Your Name and Collaborators},
123
- journal={Your Conference/Journal},
124
- year={2025}
 
 
 
125
  }
126
  ```
127
 
128
- For more details, visit [Project Repository](https://github.com/your-repo) or contact **[email protected]**.
129
 
 
21
 
22
  CALM-8B is trained on a **multi-task dataset** covering dialogue state tracking, function calling, and multi-turn reasoning. The model outperforms top proprietary and domain-specific models, including **GPT-4o**, on key evaluation benchmarks: **MultiWOZ 2.4 (TOD), BFCL V3 (LA), and API-Bank (LA).**
23
 
24
+ ## Model Sources
25
 
26
  <!-- Provide the basic links for the model. -->
27
 
28
+ - 📝 **Paper:** https://arxiv.org/abs/2502.08820
29
+ - 💻 **Repository:** https://github.com/oumi-ai/oumi/tree/main/configs/projects/calm
30
+ - 💎 **Dataset:** https://huggingface.co/datasets/uiuc-convai/CALM-IT
31
 
32
 
33
 
 
36
 
37
  - **Model Name:** CALM-8B
38
  - **Developed by:** Colloboration of UIUC Conversational AI LAB and Oumi
39
+ - **License:** cc-by-nc-4.0
40
  - **Architecture:** Fine-tuned **Llama 3.1 8B Instruct**
41
  - **Training Data:** CALM-IT dataset
42
  - **Fine-tuning Framework:** [Oumi](https://github.com/oumi-ai/oumi)
 
118
  ## Citation
119
  If you use **CALM-8B** in your research, please cite:
120
  ```
121
+ @misc{acikgoz2025singlemodelmastermultiturn,
122
+ title={Can a Single Model Master Both Multi-turn Conversations and Tool Use? CALM: A Unified Conversational Agentic Language Model},
123
+ author={Emre Can Acikgoz and Jeremiah Greer and Akul Datta and Ze Yang and William Zeng and Oussama Elachqar and Emmanouil Koukoumidis and Dilek Hakkani-Tür and Gokhan Tur},
124
+ year={2025},
125
+ eprint={2502.08820},
126
+ archivePrefix={arXiv},
127
+ primaryClass={cs.AI},
128
+ url={https://arxiv.org/abs/2502.08820},
129
  }
130
  ```
131
 
132
+ For more details, visit [Project Repository](https://github.com/oumi-ai/oumi/tree/main/configs/projects/calm) or contact **[email protected]**.
133