Instructions to use TIGER-Lab/StructLM-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/StructLM-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TIGER-Lab/StructLM-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/StructLM-13B") model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/StructLM-13B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TIGER-Lab/StructLM-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TIGER-Lab/StructLM-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TIGER-Lab/StructLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TIGER-Lab/StructLM-13B
- SGLang
How to use TIGER-Lab/StructLM-13B 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 "TIGER-Lab/StructLM-13B" \ --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": "TIGER-Lab/StructLM-13B", "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 "TIGER-Lab/StructLM-13B" \ --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": "TIGER-Lab/StructLM-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TIGER-Lab/StructLM-13B with Docker Model Runner:
docker model run hf.co/TIGER-Lab/StructLM-13B
Update README.md
Browse files
README.md
CHANGED
|
@@ -63,9 +63,9 @@ Check our Github repo for the evaluation code: [https://github.com/TIGER-AI-Lab/
|
|
| 63 |
|
| 64 |
## Prompt Format
|
| 65 |
|
| 66 |
-
**IMPORTANT
|
| 67 |
|
| 68 |
-
**For this 13B model, the prompt format is**
|
| 69 |
```
|
| 70 |
[INST] [INST] <<SYS>>
|
| 71 |
You are an AI assistant that specializes in analyzing and reasoning
|
|
|
|
| 63 |
|
| 64 |
## Prompt Format
|
| 65 |
|
| 66 |
+
\*\*\***IMPORTANT**\*\*\*
|
| 67 |
|
| 68 |
+
**For this 13B model, the prompt format (different from 7B) is**
|
| 69 |
```
|
| 70 |
[INST] [INST] <<SYS>>
|
| 71 |
You are an AI assistant that specializes in analyzing and reasoning
|