Instructions to use wAI-org/tmax-9b-capped-dppo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wAI-org/tmax-9b-capped-dppo with Transformers:

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

pipe = pipeline("text-generation", model="wAI-org/tmax-9b-capped-dppo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wAI-org/tmax-9b-capped-dppo")
model = AutoModelForCausalLM.from_pretrained("wAI-org/tmax-9b-capped-dppo", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wAI-org/tmax-9b-capped-dppo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wAI-org/tmax-9b-capped-dppo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wAI-org/tmax-9b-capped-dppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wAI-org/tmax-9b-capped-dppo

SGLang

How to use wAI-org/tmax-9b-capped-dppo 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 "wAI-org/tmax-9b-capped-dppo" \
    --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": "wAI-org/tmax-9b-capped-dppo",
		"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 "wAI-org/tmax-9b-capped-dppo" \
        --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": "wAI-org/tmax-9b-capped-dppo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wAI-org/tmax-9b-capped-dppo with Docker Model Runner:
```
docker model run hf.co/wAI-org/tmax-9b-capped-dppo
```

tmax-9b-capped-dppo — optimizer step 1000

Research checkpoint from the TMax RL study. capped DPPO arm at optimizer step 1000.

Each optimizer-step milestone is a separate branch of this repository:

from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained("wAI-org/tmax-9b-capped-dppo", revision="step1000")

Identity and provenance

field	value
stable run ID	`oscar-cap500-dppo-sandfleet__seed42__1788470999`
arm label	capped DPPO
optimizer step	1000
optimizer configuration	capped DPPO, continued to 1000 optimizer steps
base model	hamishivi/Qwen3.5-9B
`model.safetensors` sha256	`9fd1feb4fb5519781e02d6164dde0d5a8cc8d52378b46c584d54f381bf231256`

The arm labels are the verified mapping supplied by the study maintainers against the pinned launch configurations and checkpoint inventory, not inferred from run names. Steps are the trainer's own step_N HF exports, i.e. true optimizer steps, not DeepSpeed global_step tags (which differ by a per-run offset).

Files

The six files here are the checkpoint's original artifacts, unmodified. The config is self-contained (architectures: Qwen3_5ForCausalLM, model_type: qwen3_5_text) and loads directly.

Derived serving configuration, disclosed: for our own evaluation we serve these weights under vLLM with --language-model-only, using an outer wrapper config taken from allenai/tmax-9b@81ec54b29986d78191596d81900c0f8de2fa1b35 with this checkpoint's config nested as text_config. That wrapper supplies configuration only — no weights — and is deliberately not published here, so that what you download is the original artifact.

Scope and limitations

These are research checkpoints, released for inference.
Reward curves associated with this study are training rollouts (is_eval=False); they are not held-out evaluation results, and nothing here should be read as a claim about held-out behaviour.
"Reset-to-eval control" is coordination shorthand used during the study. It does not denote a particular weight-reset algorithm.

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for wAI-org/tmax-9b-capped-dppo

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

hamishivi/Qwen3.5-9B

Finetuned

(5)

this model