Instructions to use amd/AMD-OLMo-1B-SFT-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/AMD-OLMo-1B-SFT-DPO with Transformers:

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

pipe = pipeline("text-generation", model="amd/AMD-OLMo-1B-SFT-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amd/AMD-OLMo-1B-SFT-DPO")
model = AutoModelForCausalLM.from_pretrained("amd/AMD-OLMo-1B-SFT-DPO")
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

vLLM

How to use amd/AMD-OLMo-1B-SFT-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/AMD-OLMo-1B-SFT-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/AMD-OLMo-1B-SFT-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/AMD-OLMo-1B-SFT-DPO

SGLang

How to use amd/AMD-OLMo-1B-SFT-DPO 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 "amd/AMD-OLMo-1B-SFT-DPO" \
    --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": "amd/AMD-OLMo-1B-SFT-DPO",
		"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 "amd/AMD-OLMo-1B-SFT-DPO" \
        --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": "amd/AMD-OLMo-1B-SFT-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/AMD-OLMo-1B-SFT-DPO with Docker Model Runner:
```
docker model run hf.co/amd/AMD-OLMo-1B-SFT-DPO
```

Prakamya commited on Nov 17, 2025

Commit

cdb72ae

verified ·

1 Parent(s): 482f8f6

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -283,12 +283,11 @@ hf-align/scripts/run_dpo.py hf-align/recipes/AMD-OLMo-1B-dpo.yaml \
 Feel free to cite our AMD-OLMo models:
 ```bash
-@misc{AMD-OLMo,
-    title = {AMD-OLMo: A series of 1B language models trained from scratch by AMD on AMD Instinct™ MI250 GPUs.},
-    url = {https://huggingface.co/amd/AMD-OLMo},
-    author = {Jiang Liu, Jialian Wu, Prakamya Mishra, Zicheng Liu, Sudhanshu Ranjan, Pratik Prabhanjan Brahma, Yusheng Su, Gowtham Ramesh, Peng Sun, Zhe Li, Dong Li, Lu Tian, Emad Barsoum},
-    month = {October},
-    year = {2024}
 }
 ```

 Feel free to cite our AMD-OLMo models:
 ```bash
+@article{instella,
+  title={Instella: Fully Open Language Models with Stellar Performance},
+  author={Liu, Jiang and Wu, Jialian and Yu, Xiaodong and Su, Yusheng and Mishra, Prakamya and Ramesh, Gowtham and Ranjan, Sudhanshu and Manem, Chaitanya and Sun, Ximeng and Wang, Ze and Brahma, Pratik Prabhanjan and Liu, Zicheng and Barsoum, Emad},
+  journal={arXiv preprint arXiv:2511.10628},
+  year={2025}
 }
 ```