Instructions to use StanfordAIMI/GREEN-RadPhi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StanfordAIMI/GREEN-RadPhi2 with Transformers:

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

pipe = pipeline("text-generation", model="StanfordAIMI/GREEN-RadPhi2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("StanfordAIMI/GREEN-RadPhi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("StanfordAIMI/GREEN-RadPhi2", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use StanfordAIMI/GREEN-RadPhi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StanfordAIMI/GREEN-RadPhi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StanfordAIMI/GREEN-RadPhi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StanfordAIMI/GREEN-RadPhi2

SGLang

How to use StanfordAIMI/GREEN-RadPhi2 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 "StanfordAIMI/GREEN-RadPhi2" \
    --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": "StanfordAIMI/GREEN-RadPhi2",
		"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 "StanfordAIMI/GREEN-RadPhi2" \
        --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": "StanfordAIMI/GREEN-RadPhi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StanfordAIMI/GREEN-RadPhi2 with Docker Model Runner:
```
docker model run hf.co/StanfordAIMI/GREEN-RadPhi2
```

outputs_20240325

This model is a fine-tuned version of StanfordAIMI/RadPhi-2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0816

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 32
total_train_batch_size: 2048
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 12.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.1831	0.64	25	0.1257
0.1239	1.28	50	0.1044
0.108	1.92	75	0.0995
0.0976	2.56	100	0.0978
0.094	3.2	125	0.0886
0.0828	3.84	150	0.0893
0.078	4.48	175	0.0907
0.0767	5.12	200	0.0866
0.0697	5.76	225	0.0840
0.0646	6.39	250	0.0819
0.0594	7.03	275	0.0795
0.052	7.67	300	0.0795
0.0478	8.31	325	0.0803
0.0447	8.95	350	0.0786
0.0392	9.59	375	0.0800
0.038	10.23	400	0.0813
0.0357	10.87	425	0.0810
0.035	11.51	450	0.0816

Framework versions

Transformers 4.38.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 51

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for StanfordAIMI/GREEN-RadPhi2

Base model

StanfordAIMI/RadPhi-2

Finetuned

(1)

this model

Collection including StanfordAIMI/GREEN-RadPhi2

GREEN

Collection

9 items • Updated May 27, 2025 • 2