Instructions to use haohuiliang/RobustOps-RL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haohuiliang/RobustOps-RL-4B with Transformers:

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

pipe = pipeline("text-generation", model="haohuiliang/RobustOps-RL-4B")
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("haohuiliang/RobustOps-RL-4B")
model = AutoModelForCausalLM.from_pretrained("haohuiliang/RobustOps-RL-4B", 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 haohuiliang/RobustOps-RL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "haohuiliang/RobustOps-RL-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "haohuiliang/RobustOps-RL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/haohuiliang/RobustOps-RL-4B

SGLang

How to use haohuiliang/RobustOps-RL-4B 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 "haohuiliang/RobustOps-RL-4B" \
    --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": "haohuiliang/RobustOps-RL-4B",
		"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 "haohuiliang/RobustOps-RL-4B" \
        --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": "haohuiliang/RobustOps-RL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use haohuiliang/RobustOps-RL-4B with Docker Model Runner:
```
docker model run hf.co/haohuiliang/RobustOps-RL-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

RobustOps-RL-4B

English · 简体中文 · Models & data collection

GitHub: code & reproduction · Quick start · Training · Evaluation

RobustOps combines supervised fine-tuning and reinforcement learning to improve task completion and fault recovery in 4B enterprise tool agents. The GitHub project provides source code, enterprise runtime adapters, fault injection, training data, recipes and evaluation workflows.

Full-parameter RL for enterprise task completion and recovery from tool failures. Model repository.

Recommended RL evaluation model: RobustOps-RL-4B-BF16.

This FP32 export preserves weight precision for further training. Inference only needs BF16.

Training data · Trajectories.

Training

Training recipe · Environment and dependencies

Initialized from RobustOps-SFT-4B, then trained for 120 updates on Train tasks. Each update uses 16 clean and 16 fault groups with four members per group, learning rate 1e-6 and rollout temperature 1. Fault siblings continue from the same actual post-fault state to learn recovery.

Success, dependency-aware progress and successful-action quality use weights 1 / 0.3 / 0.1, normalized separately following GDPO. The initial model is Arctic-MidTool-RL-4B.

Training uses two 96 GB GPUs and a 32K context. SFT/RL share 15 validation records for supervised loss diagnostics, without training gradients. Weights are stored as FP32 and evaluated with BF16 compute.

Fixed Test results

Measure	Result
Clean task success	40/130 (30.77%)
Actual injection coverage	125/130 (96.15%)
Actual-hit task success	42/125 (33.60%)
Base/SFT/RL/teacher common-hit success	39/116 (33.62%)
Four-model common ignored-filter OOD success	7/20 (35.00%)

Evaluation fixes tasks, state, verifiers, fault mechanisms and repetition limits. Only valid zero-hit runs under these fixed settings receive supplementation, stopping on the first valid hit even when the task fails. Recovery additionally requires matched clean success. The ignored-filter family is held out of project SFT/RL.

RL uses 30.63% more completion tokens and 30.86% more tool calls than SFT. Four-model matched recovery is RL 9/10 versus SFT 10/10.

Loading

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "haohuiliang/RobustOps-RL-4B"
revision = "main"
tokenizer = AutoTokenizer.from_pretrained(repo, revision=revision)
model = AutoModelForCausalLM.from_pretrained(
    repo, revision=revision, dtype=torch.bfloat16, device_map="auto",
)

Use the supplied tool-call chat template and tool definitions, with thinking disabled. Running enterprise tasks also requires the RobustOps runtime and adapters.