Instructions to use cmu-lti/osim-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmu-lti/osim-8b with Transformers:

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

pipe = pipeline("text-generation", model="cmu-lti/osim-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("cmu-lti/osim-8b")
model = AutoModelForMultimodalLM.from_pretrained("cmu-lti/osim-8b")
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 cmu-lti/osim-8b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cmu-lti/osim-8b

SGLang

How to use cmu-lti/osim-8b 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 "cmu-lti/osim-8b" \
    --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": "cmu-lti/osim-8b",
		"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 "cmu-lti/osim-8b" \
        --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": "cmu-lti/osim-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cmu-lti/osim-8b with Docker Model Runner:
```
docker model run hf.co/cmu-lti/osim-8b
```

OSim-8B (post-trained, text)

OSim-8B is the post-trained (text) checkpoint of OSim (OdysSim), a foundation model for human behavior simulation — trained to imitate the human / user side of interactions rather than to behave as a helpful assistant. It is the text counterpart of the midtrained cmu-lti/osim-8b-mid: Qwen/Qwen3-8B midtrained on the OdysSim corpus (62 behavioral datasets along the five Soul axes — CONV/SS/COG/ROLE/EVAL) and then post-trained (task-specific RL + expert consolidation).

(Mirror of sunweiwei/OSim-8B, the text post model. For the VL variant see sunweiwei/OSim-Inst-8B.)

Intended use

Simulating the human/user side of conversations — user simulation for agent evaluation, social simulation, persona / role-play. Conditioned on a "social-context" system prompt (who is speaking: role, goal, background, style); given the other party's turns it generates the next human turn.

Results

Evaluated out-of-distribution as the user simulator in the τ-USI agentic benchmark (τ-bench airline+retail, 165 tasks, fixed GPT-5.2 agent), OSim-8B reaches USI 75.6 — the best behavioral / specialized user simulator, surpassing same-size general instruct models and every prior specialized simulator (CoSER-8B 67.2, UserLM-8B 62.0). It is distinctively human-like in reactivity (Sørensen–Dice D4 ≈ 93, matching the human inter-annotator level) and in outcome calibration (best ECE among compared models), with essentially none of the long-horizon agentic failure modes (timeouts/perseveration) seen in non-behavioral baselines.

Training

Base: Qwen3-8B
Stages: midtraining on the OdysSim corpus → task-specific reinforcement learning + expert consolidation.

Citation

If you use this model, please cite the OdysSim paper (Building Foundation Models for Human Behavior Simulation). Code: https://github.com/sunnweiwei/OdysSim