Instructions to use reshinthadith/local-repo-coder-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reshinthadith/local-repo-coder-v0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="reshinthadith/local-repo-coder-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reshinthadith/local-repo-coder-v0")
model = AutoModelForCausalLM.from_pretrained("reshinthadith/local-repo-coder-v0", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reshinthadith/local-repo-coder-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reshinthadith/local-repo-coder-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reshinthadith/local-repo-coder-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reshinthadith/local-repo-coder-v0

SGLang

How to use reshinthadith/local-repo-coder-v0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "reshinthadith/local-repo-coder-v0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reshinthadith/local-repo-coder-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "reshinthadith/local-repo-coder-v0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reshinthadith/local-repo-coder-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use reshinthadith/local-repo-coder-v0 with Docker Model Runner:
```
docker model run hf.co/reshinthadith/local-repo-coder-v0
```

local-repo-coder-v0 / example.txt

reshinthadith

Create example.txt

2ff5974 verified over 1 year ago

Raw History Blame Contribute Delete

2.5 kB

###Instruction: Generate a small python repo for matplotlib to visualize timeseries data to read from timeseries.csv file using polars. 
###Response:  The repository should include the following:
- A `src` directory for the Python source files.
- A `data` directory for the input CSV file.
- A `requirements.txt` file listing the necessary libraries.
- A `README.md` file explaining how to use the tool.
- A `run.sh` script to execute the main program.

Create the repository structure and populate it with the necessary files. ```python
<libs>matplotlib,polars</libs>
<planning>
#1 Create the repository structure.
   - Initialize the git repository.
   - Create the `src`, `data`, and `docs` directories.
#2 Populate the repository with necessary files.
   - Add a `requirements.txt` file with the necessary libraries.
   - Add a `README.md` file explaining how to use the tool.
   - Add a `run.sh` script to execute the main program.
   - Add a Python script in `src` to visualize timeseries data.
</planning>
<requirements>matplotlib==3.5.1
polars==0.17.0</requirements>
<output><file1>src/visualize_timeseries.py<content>
import polars as pl
import matplotlib.pyplot as plt

def load_timeseries_data(file_path):
    """Load timeseries data from a CSV file."""
    return pl.read_csv(file_path, has_headers=True)

def visualize_timeseries(data):
    """Visualize the timeseries data."""
    plt.figure(figsize=(10, 6))
    plt.plot(data['timestamp'], data['value'], label='Timeseries Data')
    plt.xlabel('Timestamp')
    plt.ylabel('Value')
    plt.title('Timeseries Visualization')
    plt.legend()
    plt.grid(True)
    plt.show()

if __name__ == "__main__":
    file_path = 'data/timeseries.csv'
    data = load_timeseries_data(file_path)
    visualize_timeseries(data)
</content></file1>
<bashfile>run.sh<content>python3 src/visualize_timeseries.py</content></bashfile>
<readme>README.md<content>
# Timeseries Visualization Tool

This tool visualizes timeseries data loaded from a CSV file using `pandas` for data handling and `matplotlib` for plotting.

## Requirements

Ensure you have the following libraries installed:

```bash
pip install -r requirements.txt
```

## Usage

To run the visualization tool, execute the following command:

```bash
bash run.sh
```

## Data

The tool expects a CSV file named `timeseries.csv` in the `data` directory with the following columns:
- `timestamp`: Timestamp of the data point.
- `value`: Value of the timeseries data.
</content></readme>
</output>

	###Instruction: Generate a small python repo for matplotlib to visualize timeseries data to read from timeseries.csv file using polars.
	###Response: The repository should include the following:
	- A `src` directory for the Python source files.
	- A `data` directory for the input CSV file.
	- A `requirements.txt` file listing the necessary libraries.
	- A `README.md` file explaining how to use the tool.
	- A `run.sh` script to execute the main program.

	Create the repository structure and populate it with the necessary files. ```python
	<libs>matplotlib,polars</libs>
	<planning>
	#1 Create the repository structure.
	- Initialize the git repository.
	- Create the `src`, `data`, and `docs` directories.
	#2 Populate the repository with necessary files.
	- Add a `requirements.txt` file with the necessary libraries.
	- Add a `README.md` file explaining how to use the tool.
	- Add a `run.sh` script to execute the main program.
	- Add a Python script in `src` to visualize timeseries data.
	</planning>
	<requirements>matplotlib==3.5.1
	polars==0.17.0</requirements>
	<output><file1>src/visualize_timeseries.py<content>
	import polars as pl
	import matplotlib.pyplot as plt

	def load_timeseries_data(file_path):
	"""Load timeseries data from a CSV file."""
	return pl.read_csv(file_path, has_headers=True)

	def visualize_timeseries(data):
	"""Visualize the timeseries data."""
	plt.figure(figsize=(10, 6))
	plt.plot(data['timestamp'], data['value'], label='Timeseries Data')
	plt.xlabel('Timestamp')
	plt.ylabel('Value')
	plt.title('Timeseries Visualization')
	plt.legend()
	plt.grid(True)
	plt.show()

	if __name__ == "__main__":
	file_path = 'data/timeseries.csv'
	data = load_timeseries_data(file_path)
	visualize_timeseries(data)
	</content></file1>
	<bashfile>run.sh<content>python3 src/visualize_timeseries.py</content></bashfile>
	<readme>README.md<content>
	# Timeseries Visualization Tool

	This tool visualizes timeseries data loaded from a CSV file using `pandas` for data handling and `matplotlib` for plotting.

	## Requirements

	Ensure you have the following libraries installed:

	```bash
	pip install -r requirements.txt
	```

	## Usage

	To run the visualization tool, execute the following command:

	```bash
	bash run.sh
	```

	## Data

	The tool expects a CSV file named `timeseries.csv` in the `data` directory with the following columns:
	- `timestamp`: Timestamp of the data point.
	- `value`: Value of the timeseries data.
	</content></readme>
	</output>