Instructions to use Transform72/PandasSolver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Transform72/PandasSolver with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Transform72/PandasSolver")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Transform72/PandasSolver") model = AutoModelForCausalLM.from_pretrained("Transform72/PandasSolver") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Transform72/PandasSolver with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Transform72/PandasSolver" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Transform72/PandasSolver", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Transform72/PandasSolver
- SGLang
How to use Transform72/PandasSolver 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 "Transform72/PandasSolver" \ --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": "Transform72/PandasSolver", "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 "Transform72/PandasSolver" \ --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": "Transform72/PandasSolver", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Transform72/PandasSolver with Docker Model Runner:
docker model run hf.co/Transform72/PandasSolver
Commit ·
647f9ea
1
Parent(s): b97699e
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,7 @@ tags:
|
|
| 7 |
license: llama2
|
| 8 |
---
|
| 9 |
# **PandasSolver**
|
| 10 |
-
PandasSolver is a fine-tuned generative text models with 7 billion parameters. It achieves 54.98% on [DS-1000](https://ds1000-code-gen.github.io/) Pandas Completion tasks,
|
| 11 |
-
while the accuracy of GPT-4 (August 2023 version) is 43.99%.
|
| 12 |
|
| 13 |
## Model Use
|
| 14 |
|
|
@@ -80,7 +79,7 @@ for seq in sequences:
|
|
| 80 |
|
| 81 |
## Evaluation Results
|
| 82 |
|
| 83 |
-
Performance on DS-1000:
|
| 84 |
|
| 85 |
```
|
| 86 |
Pandas Avg. Acc: 54.98%
|
|
|
|
| 7 |
license: llama2
|
| 8 |
---
|
| 9 |
# **PandasSolver**
|
| 10 |
+
PandasSolver is a fine-tuned generative text models with 7 billion parameters. It achieves 54.98% on [DS-1000](https://ds1000-code-gen.github.io/) Pandas Completion tasks, which is ~11% better than GPT-4 (43.99%, tested with August 2023 version).
|
|
|
|
| 11 |
|
| 12 |
## Model Use
|
| 13 |
|
|
|
|
| 79 |
|
| 80 |
## Evaluation Results
|
| 81 |
|
| 82 |
+
Performance on DS-1000 Completion:
|
| 83 |
|
| 84 |
```
|
| 85 |
Pandas Avg. Acc: 54.98%
|