Add link to paper and training framework

README.md

@@ -1,16 +1,10 @@
 ---
-extra_gated_heading: Acknowledge to follow corresponding license to access the repository
-extra_gated_button_content: Agree and access repository
-extra_gated_fields:
-  First Name: text
-  Last Name: text
-  Country: country
-  Affiliation: text
-license: cc-by-nc-4.0
 datasets:
 - Salesforce/xlam-function-calling-60k
 language:
 - en
+library_name: transformers
+license: cc-by-nc-4.0
 pipeline_tag: text-generation
 tags:
 - function-calling
@@ -18,9 +12,16 @@ tags:
 - tool-use
 - mistral
 - pytorch
-library_name: transformers
+extra_gated_heading: Acknowledge to follow corresponding license to access the repository
+extra_gated_button_content: Agree and access repository
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Country: country
+  Affiliation: text
 ---
 
+```markdown
 <p align="center">
 <img width="500px" alt="xLAM" src="https://huggingface.co/datasets/jianguozhang/logos/resolve/main/xlam-no-background.png">
 </p>
@@ -38,6 +39,8 @@ library_name: transformers
 Welcome to the xLAM model family! [Large Action Models (LAMs)](https://blog.salesforceairesearch.com/large-action-models/) are advanced large language models designed to enhance decision-making and translate user intentions into executable actions that interact with the world. LAMs autonomously plan and execute tasks to achieve specific goals, serving as the brains of AI agents. They have the potential to automate workflow processes across various domains, making them invaluable for a wide range of applications.
 **The model release is exclusively for research purposes. A new and enhanced version of xLAM will soon be available exclusively to customers on our Platform.**
 
+Trained with [ActionStudio: A Lightweight Framework for Data and Training of Action Models](https://huggingface.co/papers/2503.22673).
+
 ## Table of Contents
 - [Model Series](#model-series)
 - [Repository Overview](#repository-overview)
@@ -188,15 +191,35 @@ def build_conversation_history_prompt(conversation_history: str):
         })
         
     history_string = json.dumps(parsed_history)
-    return f"\n[BEGIN OF HISTORY STEPS]\n{history_string}\n[END OF HISTORY STEPS]\n"
+    return f"
+[BEGIN OF HISTORY STEPS]
+{history_string}
+[END OF HISTORY STEPS]
+"
     
     
 # Helper function to build the input prompt for our model
 def build_prompt(task_instruction: str, format_instruction: str, tools: list, query: str, conversation_history: list):
-    prompt = f"[BEGIN OF TASK INSTRUCTION]\n{task_instruction}\n[END OF TASK INSTRUCTION]\n\n"
-    prompt += f"[BEGIN OF AVAILABLE TOOLS]\n{json.dumps(xlam_format_tools)}\n[END OF AVAILABLE TOOLS]\n\n"
-    prompt += f"[BEGIN OF FORMAT INSTRUCTION]\n{format_instruction}\n[END OF FORMAT INSTRUCTION]\n\n"
-    prompt += f"[BEGIN OF QUERY]\n{query}\n[END OF QUERY]\n\n"
+    prompt = f"[BEGIN OF TASK INSTRUCTION]
+{task_instruction}
+[END OF TASK INSTRUCTION]
+
+"
+    prompt += f"[BEGIN OF AVAILABLE TOOLS]
+{json.dumps(xlam_format_tools)}
+[END OF AVAILABLE TOOLS]
+
+"
+    prompt += f"[BEGIN OF FORMAT INSTRUCTION]
+{format_instruction}
+[END OF FORMAT INSTRUCTION]
+
+"
+    prompt += f"[BEGIN OF QUERY]
+{query}
+[END OF QUERY]
+
+"
     
     if len(conversation_history) > 0: prompt += build_conversation_history_prompt(conversation_history)
     return prompt
@@ -476,4 +499,5 @@ If you find this repo helpful, please consider to cite our papers:
   journal={arXiv preprint arXiv:2402.15506},
   year={2024}
 }
+```
 ```