Instructions to use pipizhao/Pandalyst-7B-V1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipizhao/Pandalyst-7B-V1.2 with Transformers:

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

pipe = pipeline("text-generation", model="pipizhao/Pandalyst-7B-V1.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pipizhao/Pandalyst-7B-V1.2")
model = AutoModelForCausalLM.from_pretrained("pipizhao/Pandalyst-7B-V1.2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pipizhao/Pandalyst-7B-V1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pipizhao/Pandalyst-7B-V1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pipizhao/Pandalyst-7B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pipizhao/Pandalyst-7B-V1.2

SGLang

How to use pipizhao/Pandalyst-7B-V1.2 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 "pipizhao/Pandalyst-7B-V1.2" \
    --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": "pipizhao/Pandalyst-7B-V1.2",
		"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 "pipizhao/Pandalyst-7B-V1.2" \
        --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": "pipizhao/Pandalyst-7B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pipizhao/Pandalyst-7B-V1.2 with Docker Model Runner:
```
docker model run hf.co/pipizhao/Pandalyst-7B-V1.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Pandalyst: A large language model for mastering data analysis using pandas

🐱 Github Repo

What is Pandalyst

Pandalyst is a general large language model specifically trained to process and analyze data using the pandas library.

How is Pandalyst

Pandalyst has strong generalization capabilities for data tables in different fields and different data analysis needs.

Why is Pandalyst

Pandalyst is open source and free to use, and its small parameter size (7B/13B) allows us to easily deploy it on local PC.
Pandalyst can handle complex data tables (multiple columns and multiple rows), allowing us to enter enough context to describe our table in detail.
Pandalyst has very competitive performance, significantly outperforming models of the same size and even outperforming some of the strongest closed-source models.

News

🔥[2023/10/15] Now we can plot 📈! and much more powerful! We released Pandalyst-7B-V1.2, which was trained on CodeLlama-7b-Python and it surpasses ChatGPT-3.5 (2023/06/13), Pandalyst-7B-V1.1 and WizardCoder-Python-13B-V1.0 in our PandaTest_V1.0.
🤖️[2023/09/30] We released Pandalyst-7B-V1.1 , which was trained on CodeLlama-7b-Python and achieves the 76.1 exec@1 in our PandaTest_V1.0 and surpasses WizardCoder-Python-13B-V1.0 and ChatGPT-3.5 (2023/06/13).

Model	Checkpoint	Support plot	License
🔥Pandalyst-7B-V1.2	🤗 HF Link	✅	Llama2
Pandalyst-7B-V1.1	🤗 HF Link	❌	Llama2

Usage and Human evaluation

Please refer to Github.

Downloads last month: 10

Model tree for pipizhao/Pandalyst-7B-V1.2

Quantizations

3 models

Evaluation results

acc@1
self-reported

0.000