Instructions to use AIAT/Optimizer-sealion2pandas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIAT/Optimizer-sealion2pandas with Transformers:

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

pipe = pipeline("text-generation", model="AIAT/Optimizer-sealion2pandas", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIAT/Optimizer-sealion2pandas with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIAT/Optimizer-sealion2pandas"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIAT/Optimizer-sealion2pandas",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AIAT/Optimizer-sealion2pandas

SGLang

How to use AIAT/Optimizer-sealion2pandas 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 "AIAT/Optimizer-sealion2pandas" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIAT/Optimizer-sealion2pandas",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AIAT/Optimizer-sealion2pandas" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIAT/Optimizer-sealion2pandas",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AIAT/Optimizer-sealion2pandas with Docker Model Runner:
```
docker model run hf.co/AIAT/Optimizer-sealion2pandas
```

Sea-lion2pandas

fine-tuned from sea-lion-7b-instruct with question-pandas expression pairs.

How to use:

from transformers import AutoModelForCausalLM, AutoTokenizer
import pandas as pd

tokenizer = AutoTokenizer.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)

df = pd.read_csv("Your csv..")

prompt_template = "### USER:\n{human_prompt}\n\n### RESPONSE:\n"

prompt = """\
You are working with a pandas dataframe in Python. 
The name of the dataframe is `df`.
This is the result of `print(df.head())`:
{df_str}

Follow these instructions: 
1. Convert the query to executable Python code using Pandas. 
2. The final line of code should be a Python expression that can be called with the `eval()` function.
3. The code should represent a solution to the query.
4. PRINT ONLY THE EXPRESSION.
5. Do not quote the expression.
Query: {query_str} """

def create_prompt(query_str, df):
    text = prompt.format(df_str=str(df.head()), query_str=query_str)
    text = prompt_template.format(human_prompt=text)
    return text

full_prompt = create_prompt("Find test ?", df)

tokens = tokenizer(full_prompt, return_tensors="pt")
output = model.generate(tokens["input_ids"], max_new_tokens=20, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(output[0], skip_special_tokens=True))