Update README.md

README.md

@@ -16,18 +16,17 @@ language:
 
 # Model Card for Llama-3.2-1B-Instruct-APIGen-FC-v0.1
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on
-the [argilla-warehouse/apigen-synth-trl](https://huggingface.co/datasets/plaguss/apigen-synth-trl) dataset, a version of 
-[argilla-warehouse/Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla-warehouse/Synth-APIGen-v0.1) ready to do SFT.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on ç
+[argilla-warehouse/apigen-synth-trl](https://huggingface.co/datasets/argilla-warehouse/apigen-synth-trl) dataset, a version of 
+[argilla/Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla-warehouse/Synth-APIGen-v0.1) ready to do SFT on top of it.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
 
 This is a Fine tuned version of `Llama-3.2-1B-Instruct` model specific for Function Calling, to showcase how to fine tune a model on top of a dataset
-like [argilla-warehouse/Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla-warehouse/Synth-APIGen-v0.1). This dataset can be merged with the original
-[Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) and prepared with any custom format.
+like [argilla/Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1).
 
-The following examples show how to use the model with transformers, for different types of queries and availability of tools:
+### Helper functions for the prompt and output parsing
 
 <details><summary> Click to see helper functions </summary>
 
@@ -109,6 +108,11 @@ def parse_response(text: str) -> str | dict[str, any]:
 
 </details>
 
+### Examples 
+
+The following examples show how to use the model with transformers, for different types of queries and depending on the availability of tools.
+
+
 Example of *simple* function call:
 
 ````python
@@ -170,7 +174,9 @@ response = parse_response(result)
 # [{'name': 'get_weather', 'arguments': {'location': 'New York', 'unit': 'fahrenheit'}}]
 ````
 
-<details><summary> Click to see an example of parallel function call: </summary>
+#### `Parallel` function call
+
+<details><summary> Click here: </summary>
 
 ```python
 available_tools = [{"name": "spotify.play", "description": "Play specific tracks from a given artist for a specific time duration.", "parameters": {"type": "dict", "properties": {"artist": {"type": "string", "description": "The artist whose songs you want to play."}, "duration": {"type": "integer", "description": "The duration for which the songs should be played, in minutes."}}, "required": ["artist", "duration"]}}]
@@ -188,7 +194,10 @@ response = parse_response(result)
 
 </details>
 
-<details><summary> Click to see an example of multiple function calls: </summary>
+#### `Multiple` function call
+
+
+<details><summary> Click here: </summary>
 
 ```python
 available_tools = [{"name": "country_info.largest_city", "description": "Fetch the largest city of a specified country.", "parameters": {"type": "dict", "properties": {"country": {"type": "string", "description": "Name of the country."}}, "required": ["country"]}}, {"name": "country_info.capital", "description": "Fetch the capital city of a specified country.", "parameters": {"type": "dict", "properties": {"country": {"type": "string", "description": "Name of the country."}}, "required": ["country"]}}, {"name": "country_info.population", "description": "Fetch the current population of a specified country.", "parameters": {"type": "dict", "properties": {"country": {"type": "string", "description": "Name of the country."}}, "required": ["country"]}}]
@@ -206,7 +215,10 @@ response = parse_response(result)
 
 </details>
 
-<details><summary> Click to see an example of parallel multiple function calls: </summary>
+#### `Parallel multiple` function call
+
+
+<details><summary> Click here: </summary>
 
 ```python
 available_tools = [{"name": "math_toolkit.sum_of_multiples", "description": "Find the sum of all multiples of specified numbers within a specified range.", "parameters": {"type": "dict", "properties": {"lower_limit": {"type": "integer", "description": "The start of the range (inclusive)."}, "upper_limit": {"type": "integer", "description": "The end of the range (inclusive)."}, "multiples": {"type": "array", "items": {"type": "integer"}, "description": "The numbers to find multiples of."}}, "required": ["lower_limit", "upper_limit", "multiples"]}}, {"name": "math_toolkit.product_of_primes", "description": "Find the product of the first n prime numbers.", "parameters": {"type": "dict", "properties": {"count": {"type": "integer", "description": "The number of prime numbers to multiply together."}}, "required": ["count"]}}]
@@ -224,7 +236,10 @@ response = parse_response(result)
 
 </details>
 
-<details><summary> Click to see an example of multi-turn function call: </summary>
+#### `Multi-turn` function call
+
+
+<details><summary> Click here: </summary>
 
 ```python
 
@@ -280,7 +295,10 @@ response = parse_response(result)
 
 </details>
 
-<details><summary> Click to see an example of irrelevance function call: </summary>
+#### `Irrelevance` function call (examples when some data is missing)
+
+
+<details><summary> Click here: </summary>
 
 Example response with no tools available
 
@@ -334,7 +352,7 @@ response = parse_response(result)
 
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/plaguss/huggingface/runs/dw9q43g4)
 
-This model was trained with SFT. You can take a look at [sft.slurm](https://huggingface.co/plaguss/Llama-3.2-1B-Instruct-APIGen-FC-v0.1/blob/main/sft.slurm) to see the
+This model was trained with SFT. You can take a look at [sft.slurm](https://huggingface.co/argilla/Llama-3.2-1B-Instruct-APIGen-FC-v0.1/blob/main/sft.slurm) to see the
 training script, if you don't have access to a slurm cluster, it can be run jsut using the `accelerate` command. It took 13 minutes in a node with 8xH100.
 
 To install the requirements, the following commands can be used:
@@ -360,8 +378,6 @@ And login to your WandB and Hugging Face accounts to push both logs and the fina
 
 ## Citations
 
-
-
 Cite TRL as:
     
 ```bibtex