Instructions to use NextGLab/ORANSight_LLama_70B_Instruct_AQLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NextGLab/ORANSight_LLama_70B_Instruct_AQLM with Transformers:

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

pipe = pipeline("text-generation", model="NextGLab/ORANSight_LLama_70B_Instruct_AQLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NextGLab/ORANSight_LLama_70B_Instruct_AQLM", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NextGLab/ORANSight_LLama_70B_Instruct_AQLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NextGLab/ORANSight_LLama_70B_Instruct_AQLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NextGLab/ORANSight_LLama_70B_Instruct_AQLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NextGLab/ORANSight_LLama_70B_Instruct_AQLM

SGLang

How to use NextGLab/ORANSight_LLama_70B_Instruct_AQLM 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 "NextGLab/ORANSight_LLama_70B_Instruct_AQLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NextGLab/ORANSight_LLama_70B_Instruct_AQLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "NextGLab/ORANSight_LLama_70B_Instruct_AQLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NextGLab/ORANSight_LLama_70B_Instruct_AQLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NextGLab/ORANSight_LLama_70B_Instruct_AQLM with Docker Model Runner:
```
docker model run hf.co/NextGLab/ORANSight_LLama_70B_Instruct_AQLM
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for ORANSight Llama-70B

This model belongs to the first release of the ORANSight family of models.

Developed by: NextG lab@ NC State
License: llama3.1
Context Window 128K tokens.
Fine Tuning Framework: AQLM

Note: This only contains the LoRA adapters and the Tokenizer obtained by leveraging QLoRA with AQLM's 2-Bit implementation.

Generate with Transformers

Below is a quick example of how to use the model with Hugging Face Transformers:

from transformers import pipeline

# Example query
messages = [
    {"role": "system", "content": "You are an O-RAN expert assistant."},
    {"role": "user", "content": "Explain the E2 interface."},
]

# Load the model
chatbot = pipeline("text-generation", model="NextGLab/ORANSight_LLama_70B_Instruct")
result = chatbot(messages)
print(result)

Coming Soon

A detailed paper documenting the experiments and results achieved with this model will be available soon. Meanwhile, if you try this model, please cite the below mentioned paper to acknowledge the foundational work that enabled this fine-tuning.

@article{gajjar2024oran,
  title={Oran-bench-13k: An open source benchmark for assessing llms in open radio access networks},
  author={Gajjar, Pranshav and Shah, Vijay K},
  journal={arXiv preprint arXiv:2407.06245},
  year={2024}
}