Instructions to use NeuML/Llama-3.1_OpenScholar-8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeuML/Llama-3.1_OpenScholar-8B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="NeuML/Llama-3.1_OpenScholar-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeuML/Llama-3.1_OpenScholar-8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("NeuML/Llama-3.1_OpenScholar-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeuML/Llama-3.1_OpenScholar-8B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeuML/Llama-3.1_OpenScholar-8B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuML/Llama-3.1_OpenScholar-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeuML/Llama-3.1_OpenScholar-8B-AWQ

SGLang

How to use NeuML/Llama-3.1_OpenScholar-8B-AWQ 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 "NeuML/Llama-3.1_OpenScholar-8B-AWQ" \
    --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": "NeuML/Llama-3.1_OpenScholar-8B-AWQ",
		"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 "NeuML/Llama-3.1_OpenScholar-8B-AWQ" \
        --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": "NeuML/Llama-3.1_OpenScholar-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeuML/Llama-3.1_OpenScholar-8B-AWQ with Docker Model Runner:
```
docker model run hf.co/NeuML/Llama-3.1_OpenScholar-8B-AWQ
```

Llama-3.1_OpenScholar-8B with AWQ Quantization

This is Llama-3.1_OpenScholar-8B with AWQ Quantization applied using the following code.

Based on this example code.

import torch

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

# Input and output path
path = "OpenScholar/Llama-3.1_OpenScholar-8B"
output = "Llama-3.1_OpenScholar-8B-AWQ"

# Quantization config
config = {
    "zero_point": True,
    "q_group_size": 128,
    "w_bit": 4,
    "version": "GEMM"
}

# Load model
model = AutoAWQForCausalLM.from_pretrained(
    model_path=path,
    low_cpu_mem_usage=True,
    use_cache=False,
    safetensors=False,
    device_map="cuda",
    torch_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(path)

# Quantize
model.quantize(tokenizer, quant_config=config)

# Save quantized model
model.save_quantized(output)

# Save tokenizer
# Note: Transformers >= 4.45.0 doubles size of tokenizer.json
# See https://github.com/huggingface/transformers/issues/34744
tokenizer.save_pretrained(output)

print(f'Model is quantized and saved to "{output}"')