Instructions to use jmeadows17/MathT5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jmeadows17/MathT5-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jmeadows17/MathT5-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("jmeadows17/MathT5-large") model = AutoModelForSeq2SeqLM.from_pretrained("jmeadows17/MathT5-large") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use jmeadows17/MathT5-large with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jmeadows17/MathT5-large" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jmeadows17/MathT5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jmeadows17/MathT5-large
- SGLang
How to use jmeadows17/MathT5-large 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 "jmeadows17/MathT5-large" \ --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": "jmeadows17/MathT5-large", "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 "jmeadows17/MathT5-large" \ --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": "jmeadows17/MathT5-large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jmeadows17/MathT5-large with Docker Model Runner:
docker model run hf.co/jmeadows17/MathT5-large
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,7 @@ It was trained on 155 physics symbols, but struggles with out-of-vocabulary symb
|
|
| 21 |
|
| 22 |
**Example prompt:**
|
| 23 |
|
| 24 |
-
```prompt = "Given \\cos{(q)} = \\theta{(q)},
|
| 25 |
-
then derive - \\sin{(q)} = \\frac{d}{d q} \\theta{(q)},
|
| 26 |
-
then obtain (- \\sin{(q)})^{q} (\\frac{d}{d q} \\cos{(q)})^{q} = (- \\sin{(q)})^{2 q}"```
|
| 27 |
|
| 28 |
Output derivations are equations separated by "and".
|
| 29 |
|
|
|
|
| 21 |
|
| 22 |
**Example prompt:**
|
| 23 |
|
| 24 |
+
```prompt = "Given \\cos{(q)} = \\theta{(q)}, then derive - \\sin{(q)} = \\frac{d}{d q} \\theta{(q)}, then obtain (- \\sin{(q)})^{q} (\\frac{d}{d q} \\cos{(q)})^{q} = (- \\sin{(q)})^{2 q}"```
|
|
|
|
|
|
|
| 25 |
|
| 26 |
Output derivations are equations separated by "and".
|
| 27 |
|