Update README.md

README.md

@@ -8,15 +8,14 @@ tags: []
 This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) for the **Function Calling** task on non-synthetic data, 
 fully annotated by humans only, on the English version of the <ins>*DiTy/function-calling*</ins> dataset.
 <!-- Provide a quick summary of what the model is/does. -->
---
----
+
 ## Model card tree
 
 * [How prepare your functions (tools) for *Function Calling*](#prepare_func_call)
+* [Just use chat template for generation](#just_chat_template)
+* [Prompt structure and expected content](#roles)
 
-
-
-
+<br>
 
 ## Usage (HuggingFace Transformers)
 
@@ -52,12 +51,256 @@ def get_sunrise_sunset_times(city: str):
     return ["6:00 AM", "6:00 PM"]
 ```
 
-### Using transformers
+### <a name="just_chat_template"></a>Just use chat template
+
+Next, you need to download the model and tokenizer:
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained(
+    "DiTy/gemma-2-9b-it-function-calling",
+    device_map="auto",
+    torch_dtype=torch.bfloat16,  # use float16 or float32 if bfloat16 is not available to you.
+    cache_dir=PATH_TO_MODEL_DIR,  # optional
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "DiTy/gemma-2-9b-it-function-calling",
+    cache_dir=PATH_TO_MODEL_DIR,  # optional
+)
+```
+
+To get the result of generation, just use `apply_chat_template`. In order to take into account our written functions (tools), 
+we need to pass them as a list through the `tools` attribute and also use `add_prompt_generation=True`.
+```python
+history_messages = [
+    {"role": "system", "content": "You are a helpful assistant with access to the following functions. Use them if required - "},
+    {"role": "user", "content": "Hi, can you tell me the time of sunrise in Los Angeles?"},
+]
+
+inputs = tokenizer.apply_chat_template(
+    history_messages,
+    tokenize=False,
+    add_generation_prompt=True,  # adding prompt for generation
+    tools=[get_weather, get_sunrise_sunset_times],  # our functions (tools)
+)
+```
+
+Then our `inputs` will look like this:
+```
+<bos><start_of_turn>user
+You are a helpful assistant with access to the following functions. Use them if required - {
+    "name": "get_weather",
+    "description": "A function that returns the weather in a given city.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "city": {
+                "type": "string",
+                "description": "The city to get the weather for."
+            }
+        },
+        "required": [
+            "city"
+        ]
+    }
+},
+{
+    "name": "get_sunrise_sunset_times",
+    "description": "A function that returns the time of sunrise and sunset at the present moment, for a given city, in the form of a list: [sunrise_time, sunset_time].",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "city": {
+                "type": "string",
+                "description": "The city to get the sunrise and sunset times for."
+            }
+        },
+        "required": [
+            "city"
+        ]
+    }
+}
+
+Hi, can you tell me the time of sunrise in Los Angeles?<end_of_turn>
+<start_of_turn>model
+
+```
+
+Now we can generate a model's response. 
+Be careful because, after `apply_chat_template`, there is no need to *add special tokens* during tokenization. So, use `add_special_tokens=False`:
+```python
+terminator_ids = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<end_of_turn>"),
+]
+
+prompt_ids =  tokenizer.encode(inputs, add_special_tokens=False, return_tensors='pt').to(model.device)
+generated_ids = model.generate(
+    prompt_ids,
+    max_new_tokens=512,
+    eos_token_id=terminator_ids,
+    bos_token_id=tokenizer.bos_token_id,
+)
+generated_response = tokenizer.decode(generated_ids[0][prompt_ids.shape[-1]:], skip_special_tokens=False)  # `skip_special_tokens=False` for debug 
+```
+
+We get the generation as a function call:
+```
+Function call: {"name": "get_sunrise_sunset_times", "arguments": {"city": "Los Angeles"}}<end_of_turn>
+```
+
+Great, now we can pick up and process the results with our *called function*, and then provide the model with the *function's response*:
+```python
+history_messages = [
+    {"role": "system", "content": "You are a helpful assistant with access to the following functions. Use them if required - "},
+    {"role": "user", "content": "Hi, can you tell me the time of sunrise in Los Angeles?"},
+    {"role": "function-call", "content": '{"name": "get_sunrise_sunset_times", "arguments": {"city": "Los Angeles"}}'},
+    {"role": "function-response", "content": '{"times_list": ["6:00 AM", "6:00 PM"]}'},  # a hypothetical response from our function
+]
+
+inputs = tokenizer.apply_chat_template(
+    history_messages,
+    tokenize=False,
+    add_generation_prompt=True,  # adding prompt for generation
+    tools=[get_weather, get_sunrise_sunset_times],  # our functions (tools)
+)
+```
+
+Let's make sure the `inputs` are correct:
+```
+<bos><start_of_turn>user
+You are a helpful assistant with access to the following functions. Use them if required - {
+    "name": "get_weather",
+    "description": "A function that returns the weather in a given city.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "city": {
+                "type": "string",
+                "description": "The city to get the weather for."
+            }
+        },
+        "required": [
+            "city"
+        ]
+    }
+},
+{
+    "name": "get_sunrise_sunset_times",
+    "description": "A function that returns the time of sunrise and sunset at the present moment, for a given city, in the form of a list: [sunrise_time, sunset_time].",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "city": {
+                "type": "string",
+                "description": "The city to get the sunrise and sunset times for."
+            }
+        },
+        "required": [
+            "city"
+        ]
+    }
+}
+
+Hi, can you tell me the time of sunrise in Los Angeles?<end_of_turn>
+<start_of_turn>model
+Function call: {"name": "get_sunrise_sunset_times", "arguments": {"city": "Los Angeles"}}<end_of_turn>
+<start_of_turn>user
+Function response: {"times_list": ["6:00 AM", "6:00 PM"]}<end_of_turn>
+<start_of_turn>model
+
+```
+
+Similarly, we generate a response from the model:
+```python
+prompt_ids =  tokenizer.encode(inputs, add_special_tokens=False, return_tensors='pt').to(model.device)
+generated_ids = model.generate(
+    prompt_ids,
+    max_new_tokens=512,
+    eos_token_id=terminator_ids,
+    bos_token_id=tokenizer.bos_token_id,
+)
+generated_response = tokenizer.decode(generated_ids[0][prompt_ids.shape[-1]:], skip_special_tokens=False)  # `skip_special_tokens=False` for debug
+```
+
+As a result, we get the model's response:
+```
+The sunrise time in Los Angeles is 6:00 AM.<end_of_turn>
+```
+
+## Usage via transformers `pipeline`
+
+<details>
+  <summary>
+  Generation via pipeline
+  </summary>
 
 ```python
+from transformers import pipeline
+
+
+generation_pipeline = pipeline(
+    "text-generation",
+    model="DiTy/gemma-2-9b-it-function-calling",
+    model_kwargs={
+        "torch_dtype": torch.bfloat16,  # use float16 or float32 if bfloat16 is not supported for you. 
+        "cache_dir": PATH_TO_MODEL_DIR,  # OPTIONAL
+    },
+    device_map="auto",
+)
+
+history_messages = [
+    {"role": "system", "content": "You are a helpful assistant with access to the following functions. Use them if required - "},
+    {"role": "user", "content": "Hi, can you tell me the time of sunrise in Los Angeles?"},
+    {"role": "function-call", "content": '{"name": "get_sunrise_sunset_times", "arguments": {"city": "Los Angeles"}}'},
+    {"role": "function-response", "content": '{"times_list": ["6:00 AM", "6:00 PM"]}'},
+]
+
+inputs = generation_pipeline.tokenizer.apply_chat_template(
+    history_messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    tools=[get_weather, get_sunrise_sunset_times],
+)
+
+terminator_ids = [
+    generation_pipeline.tokenizer.eos_token_id,
+    generation_pipeline.tokenizer.convert_tokens_to_ids("<end_of_turn>")
+]
+
+outputs = generation_pipeline(
+    inputs,
+    max_new_tokens=512,
+    eos_token_id=terminator_ids,
+)
+
+print(outputs[0]["generated_text"][len(inputs):])
+```
+  
+</details>
+
+## <a name="roles"></a>Prompt structure and expected content
 
+For the most correct operation of the model, it is assumed that `apply_chat_template` will be used. 
+It is necessary to transmit the message history in a certain format.
+```python
+history_messages = [
+    {"role": "...", "content": "..."},
+    ...
+]
 ```
 
+The following roles are available for use:
+
+* `system` - an optional role, its content is always placed at the very beginning and before listing the functions available to the model (tools).
+You can always use the standard option that was used during the training: ***"You are a helpful assistant with access to the following functions. Use them if required - "***
+* `user` - the user's request is transmitted through this role.
+* `function-call` - The body of the function call is passed through this role.
+Although the model is trained to generate a function call in the form of ***"Function call: {...}\<end_of_turn\>"***, you should still pass only the body ***"{...}"***
+to the *"content"* field, since using `apply_chat_template`, the postscript in the instructions is added automatically.
+* `function-response` - 
+* `model` -