Instructions to use SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True with Transformers:

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

pipe = pipeline("text-generation", model="SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True")
model = AutoModelForCausalLM.from_pretrained("SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True

SGLang

How to use SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True 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 "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True" \
    --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": "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True",
		"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 "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True" \
        --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": "SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True with Docker Model Runner:
```
docker model run hf.co/SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True
```

Quantized version of Universal-NER/UniNER-7B-definition

Universal-NER/UniNER-7B-definition quantized to 4bit with GPTQ and stored with 1GB shard size.

Model Description

The model Universal-NER/UniNER-7B-definition was quantized to 4bit, group_size 128, and act-order=True with auto-gptq integration in transformers (https://huggingface.co/blog/gptq-integration).

Evaluation

TODO

Prompt template

Prompt template is the same as for the full precision model:

prompt_template = """A virtual assistant answers questions from a user based on the provided text.
USER: Text: {input_text}
ASSISTANT: I’ve read this text.
USER: What describes {entity_name} in the text?
ASSISTANT:
"""

Usage

It is recommended to format input according to the prompt template mentioned above during inference for best results.

prompt = prompt_template.format_map({"input_text": "Cologne is a great city in Germany - maybe even the greatest ;)", "entity_name": "city"})

The model is small enough to be loaded in free-tier Colab with a T4 GPU: https://gist.github.com/sebastianschramm/b849c06676c6601d9a87270e83f5a157

License

The original full precision model and its associated data are released under the CC BY-NC 4.0 license. Hence, the same license applies for the 4bit version.

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

I32

F16

Collection including SebastianSchramm/UniNER-7B-definition-GPTQ-4bit-128g-actorder_True

UniversalNER 4bit

Collection

4bit versions of UniversalNER models • 4 items • Updated Nov 13, 2023 • 2