Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
metrics:
|
|
@@ -16,7 +16,7 @@ base_model:
|
|
| 16 |
|
| 17 |
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).**
|
| 18 |
|
| 19 |
-
## Model Sources [
|
| 20 |
|
| 21 |
<!-- Provide the basic links for the model. -->
|
| 22 |
|
|
@@ -90,6 +90,9 @@ TODO
|
|
| 90 |
- **Scalability to Larger Models:** Future iterations (CALM-70B, CALM-405B) extend capabilities to larger-scale agentic conversations.
|
| 91 |
- **Open-Source Expansion:** All datasets, training scripts, and model checkpoints are publicly available to foster further research.
|
| 92 |
|
|
|
|
|
|
|
|
|
|
| 93 |
<!-- TODO -->
|
| 94 |
---
|
| 95 |
## Citation
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
metrics:
|
|
|
|
| 16 |
|
| 17 |
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).**
|
| 18 |
|
| 19 |
+
## Model Sources [TODO]
|
| 20 |
|
| 21 |
<!-- Provide the basic links for the model. -->
|
| 22 |
|
|
|
|
| 90 |
- **Scalability to Larger Models:** Future iterations (CALM-70B, CALM-405B) extend capabilities to larger-scale agentic conversations.
|
| 91 |
- **Open-Source Expansion:** All datasets, training scripts, and model checkpoints are publicly available to foster further research.
|
| 92 |
|
| 93 |
+
## License
|
| 94 |
+
This model is licensed under **cc-by-nc-4.0**.
|
| 95 |
+
|
| 96 |
<!-- TODO -->
|
| 97 |
---
|
| 98 |
## Citation
|