Instructions to use Orkhan/llama-2-7b-absa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Orkhan/llama-2-7b-absa with Transformers:

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

pipe = pipeline("text-generation", model="Orkhan/llama-2-7b-absa")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Orkhan/llama-2-7b-absa")
model = AutoModelForCausalLM.from_pretrained("Orkhan/llama-2-7b-absa", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Orkhan/llama-2-7b-absa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Orkhan/llama-2-7b-absa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orkhan/llama-2-7b-absa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Orkhan/llama-2-7b-absa

SGLang

How to use Orkhan/llama-2-7b-absa 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 "Orkhan/llama-2-7b-absa" \
    --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": "Orkhan/llama-2-7b-absa",
		"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 "Orkhan/llama-2-7b-absa" \
        --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": "Orkhan/llama-2-7b-absa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Orkhan/llama-2-7b-absa with Docker Model Runner:
```
docker model run hf.co/Orkhan/llama-2-7b-absa
```

No module named 'transformers.models.fuyu.configuration_fuyu'

by sq428 - opened Mar 20, 2024

Discussion

sq428

Mar 20, 2024

hello, thank you for your teaching. And when I run the example code, I find that I have an error that:
ModuleNotFoundError: No module named 'transformers.models.fuyu.configuration_fuyu'

The above exception was the direct cause of the following exception:

RuntimeError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/transformers/utils/import_utils.py in _get_module(self, module_name)

RuntimeError: Failed to import transformers.models.fuyu.configuration_fuyu because of the following error (look up to see its traceback):
No module named 'transformers.models.fuyu.configuration_fuyu'

Orkhan

Owner Mar 21, 2024

Hi,

I just used the notebook from scratch, and it worked. Could you please tell me at what step it happened and if you've installed all the packages with their indicated versions?

sq428

Mar 21, 2024

Thank you for your replying. Maybe it's my mistake.I will try it again

Orkhan changed discussion status to closed Mar 21, 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