Update README.md

README.md

@@ -1,16 +1,25 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- LAM
+- tooluse
+- function calling
+license: mit
+datasets:
+- Salesforce/xlam-function-calling-60k
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
+ActionGemma is a LargeActionModel inspired from Salesforce/xLAM and trained on it's dataset. this is a combination of multi-lingual capabilities of Gemma with Function calling capabilites from xLAM dataset
+Now you have a Action /function calling Model for all the languages supported by gemma2
 
 
 ## Model Details
 
+Base Model : Gemma2-9B-it
+Fine-Tuned on : xLAM dataset
+
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
@@ -40,7 +49,124 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 ### Direct Use
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
+tokenizer in built have a chat template as follows
+```
+tokenizer = AutoTokenizer.from_pretrained("KishoreK/ActionGemma-9B")
+tokenizer.chat_template = """{{ bos_token }}
+{% for message in messages %}
+    {% if message['role'] == 'tools' %}
+        {{ '<unused0>\n' + message['content'] + '<unused1>\n'}}
+    {% else %}
+      {{ '<start_of_turn>' + message['role'] + '\n' + message['content'] | trim + '<end_of_turn>\n' }}
+  {% endif %}
+{% endfor %}
+
+{% if add_generation_prompt %}
+  {{ '<start_of_turn>assistant\n' }}
+{% endif %}
+"""
+```
+you can utilise this or modify based on this syntax.
+
+```
+task_instruction = """
+You are an expert in composing functions. You are given a question and a set of possible functions. 
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose. 
+If none of the functions can be used, point it out and refuse to answer. 
+If the given question lacks the parameters required by the function, also point it out.
+""".strip()
+
+get_weather_api = {
+    "name": "get_weather",
+    "description": "Get the current weather for a location",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, New York"
+            },
+            "unit": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The unit of temperature to return"
+            }
+        },
+        "required": ["location"]
+    }
+}
+
+search_api = {
+    "name": "search",
+    "description": "Search for information on the internet",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "query": {
+                "type": "string",
+                "description": "The search query, e.g. 'latest news on AI'"
+            }
+        },
+        "required": ["query"]
+    }
+}
+
+openai_format_tools = [get_weather_api, search_api]
+
+def convert_to_xlam_tool(tools):
+    ''''''
+    if isinstance(tools, dict):
+        return {
+            "name": tools["name"],
+            "description": tools["description"],
+            "parameters": {k: v for k, v in tools["parameters"].get("properties", {}).items()}
+        }
+    elif isinstance(tools, list):
+        return [convert_to_xlam_tool(tool) for tool in tools]
+    else:
+        return tools
+
+user_query = "अमेरिका के राष्ट्रपति कौन है?"
+tools = openai_format_tools
+messages = [{
+    "role" : "system",
+    "content" : task_instruction
+},{
+    "role" : "user",
+    "content" : user_query
+},{
+    "role": "tools",
+    "content": json.dumps(convert_to_xlam_tool(tools))
+}]
+
+print(tokenizer.decode(tokenizer.apply_chat_template(messages, add_generation_prompt=True)))
+```
+
+sample response from applied chat template 
+```
+<bos>
+      <start_of_turn>system
+You are an expert in composing functions. You are given a question and a set of possible functions. 
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose. 
+If none of the functions can be used, point it out and refuse to answer. 
+If the given question lacks the parameters required by the function, also point it out.<end_of_turn>
+
+      <start_of_turn>user
+अमेरिका के राष्ट्रपति कौन है?<end_of_turn>
+
+        <unused0>
+[{"name": "get_weather", "description": "Get the current weather for a location", "parameters": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, New York"}, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return"}}}, {"name": "search", "description": "Search for information on the internet", "parameters": {"query": {"type": "string", "description": "The search query, e.g. 'latest news on AI'"}}}]<unused1>
+
+
+  <start_of_turn>assistant
+```
+invoking model with this prompt
+```
+model = AutoModelForCausalLM.from_pretrained("KishoreK/ActionGemma-9B", use_cache=True)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
+```
+chat template, inference are referenced from xLAM documentation.
 [More Information Needed]
 
 ### Downstream Use [optional]