Instructions to use simonlqy/SkillGate-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simonlqy/SkillGate-9B with Transformers:

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

pipe = pipeline("text-generation", model="simonlqy/SkillGate-9B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("simonlqy/SkillGate-9B")
model = AutoModelForMultimodalLM.from_pretrained("simonlqy/SkillGate-9B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use simonlqy/SkillGate-9B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/simonlqy/SkillGate-9B

SGLang

How to use simonlqy/SkillGate-9B 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 "simonlqy/SkillGate-9B" \
    --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": "simonlqy/SkillGate-9B",
		"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 "simonlqy/SkillGate-9B" \
        --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": "simonlqy/SkillGate-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use simonlqy/SkillGate-9B with Docker Model Runner:
```
docker model run hf.co/simonlqy/SkillGate-9B
```

SkillGate-9B

Policy from "SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents."

Agent frameworks expose skills — instruction files with a name, a one-line description and a body — by progressive disclosure: the agent sees only names and descriptions and must open a file to learn what is inside. With thousands of skills in a library, which one to read becomes a decision the policy makes mid-episode, and outcome-rewarded RL cannot teach it: the tokens naming the chosen skill carry a median 0.14% of their trajectory's loss weight, and two in five of them receive a negative advantage because execution afterwards failed.

SkillGate partitions one trajectory's token support into two disjoint credit channels: outcome credit reaches only execution tokens (the whole skill-read call is removed from the task loss), while an action-local advantage reaches exactly the skill-naming tokens, positive only when the trajectory's single read is the correct skill.

Model


Base	Qwen3.5-9B
Training	100 steps on-policy GRPO, 491 tasks, 8 rollouts/prompt, global batch 128, lr 1e-6, KL 3e-5, selector coefficient 0.20
Checkpoint	`iter_0000099`, the final step (`selection_role: final`)
Architecture	`Qwen3_5ForConditionalGeneration`

Results (385-trial protocol, 5 agentic benchmarks, 16-candidate slate)

Method	Overall	Oracle read	Misleading read
SFT (RL init)	40.8	37.9	61.8
SkillRL (outcome reward only)	47.0	54.3	69.6
SkillGate	53.2	83.9	21.8

Same initialisation, data, steps and hyperparameters as the outcome-only row; the only difference is which tokens the gradient reaches.

Intended use

Research on agentic skill/tool selection. The model expects the OpenClaw-style prompt profile and tool schema used in the paper; see the repository for the exact system prompt and the frozen skill slates.

License

Derived from Qwen3.5-9B and distributed under the Qwen license; see license_link.

Downloads last month: 163

Safetensors

Model size

10B params

Tensor type

BF16

Model tree for simonlqy/SkillGate-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(618)

this model