Update README.md
Browse files
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
|
25 |
|
26 |
<!-- Provide the basic links for the model. -->
|
27 |
|
28 |
-
- **Paper
|
29 |
-
- **Repository:**
|
|
|
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:**
|
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 |
-
@
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
|
|
|
|
|
|
125 |
}
|
126 |
```
|
127 |
|
128 |
-
For more details, visit [Project Repository](https://github.com/
|
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 |
|