Instructions to use RUCKBReasoning/TableLLM-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RUCKBReasoning/TableLLM-13b with Transformers:

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

pipe = pipeline("text-generation", model="RUCKBReasoning/TableLLM-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RUCKBReasoning/TableLLM-13b")
model = AutoModelForCausalLM.from_pretrained("RUCKBReasoning/TableLLM-13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RUCKBReasoning/TableLLM-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RUCKBReasoning/TableLLM-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RUCKBReasoning/TableLLM-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RUCKBReasoning/TableLLM-13b

SGLang

How to use RUCKBReasoning/TableLLM-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 "RUCKBReasoning/TableLLM-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": "RUCKBReasoning/TableLLM-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 "RUCKBReasoning/TableLLM-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": "RUCKBReasoning/TableLLM-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RUCKBReasoning/TableLLM-13b with Docker Model Runner:
```
docker model run hf.co/RUCKBReasoning/TableLLM-13b
```

KAKA22 commited on Feb 7, 2024

Commit

cd84e92

verified ·

1 Parent(s): cac21c2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -24,8 +24,8 @@ We evaluate the code solution generation ability of TLLM on three benchmarks: Wi
 | StructGPT (GPT3.5)   |  52.5  |  27.5  |  11.8  |  14.0   |   67.8  |**84.8**|       /      |   48.9  |
 | Binder (GPT3.5)      |  61.6  |  12.8  |   6.8  |   5.1   |   78.6  |  52.6  |       /      |   42.5  |
 | DATER (GPT3.5)       |  53.4  |  28.4  |  18.3  |  13.0   |   58.2  |  26.5  |       /      |   37.0  |
-| TLLM-7B (Ours)       |  58.8  |  66.9  |  72.6  |<ins>63.1</ins>|<ins>86.6</ins>|  82.6  |<ins>78.8</ins>|   72.8  |
-| TLLM-13B (Ours)      |<ins>62.4</ins>|  68.2  |<ins>74.5</ins>|  62.5   | **90.7**|<ins>83.4</ins>|   **80.8**   |<ins>74.7</ins>|
 ## Prompt Template
 The prompts we used for generating code solutions and text answers are introduced below.

 | StructGPT (GPT3.5)   |  52.5  |  27.5  |  11.8  |  14.0   |   67.8  |**84.8**|       /      |   48.9  |
 | Binder (GPT3.5)      |  61.6  |  12.8  |   6.8  |   5.1   |   78.6  |  52.6  |       /      |   42.5  |
 | DATER (GPT3.5)       |  53.4  |  28.4  |  18.3  |  13.0   |   58.2  |  26.5  |       /      |   37.0  |
+| TableLLM-7B (Ours)   |  58.8  |  66.9  |  72.6  |<ins>63.1</ins>|<ins>86.6</ins>|  82.6  |<ins>78.8</ins>|   72.8  |
+| TableLLM-13B (Ours)  |<ins>62.4</ins>|  68.2  |<ins>74.5</ins>|  62.5   | **90.7**|<ins>83.4</ins>|   **80.8**   |<ins>74.7</ins>|
 ## Prompt Template
 The prompts we used for generating code solutions and text answers are introduced below.