Instructions to use RUCKBReasoning/TableLLM-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RUCKBReasoning/TableLLM-7b with Transformers:

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

pipe = pipeline("text-generation", model="RUCKBReasoning/TableLLM-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("RUCKBReasoning/TableLLM-7b")
model = AutoModelForMultimodalLM.from_pretrained("RUCKBReasoning/TableLLM-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RUCKBReasoning/TableLLM-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RUCKBReasoning/TableLLM-7b"
# 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-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RUCKBReasoning/TableLLM-7b

SGLang

How to use RUCKBReasoning/TableLLM-7b 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-7b" \
    --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-7b",
		"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-7b" \
        --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-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RUCKBReasoning/TableLLM-7b with Docker Model Runner:
```
docker model run hf.co/RUCKBReasoning/TableLLM-7b
```

Specifying CodeLlama type

by mehti - opened Aug 29, 2024

Discussion

mehti

Aug 29, 2024

Hello,

Thanks a lot for your work. Could you please specify in the documentation which CodeLlama you used for fine-tuning? There are three types: CodeLlama-7b-hf, CodeLlama-7b-Instruct-hf, and CodeLlama-7b-Python-hf.
I assume it's meta-llama/CodeLlama-7b-Instruct-hf, but it would also be nice to have it in the documentation.

Thank you in advance.

BR,
Mehti

KAKA22

RUCKBReasoning org Sep 2, 2024

Hi,

Thanks for your advise! We use meta-llama/CodeLlama-7b-Instruct-hf as our backbone for fine-tuning. We will add this information in the README.md.

Zeyao
TableLLM Team

KAKA22 changed discussion status to closed Sep 2, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment