Instructions to use yinita/ps4mas-sft-x5-single-ep3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yinita/ps4mas-sft-x5-single-ep3 with Transformers:

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

pipe = pipeline("text-generation", model="yinita/ps4mas-sft-x5-single-ep3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yinita/ps4mas-sft-x5-single-ep3")
model = AutoModelForCausalLM.from_pretrained("yinita/ps4mas-sft-x5-single-ep3", 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 yinita/ps4mas-sft-x5-single-ep3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yinita/ps4mas-sft-x5-single-ep3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yinita/ps4mas-sft-x5-single-ep3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yinita/ps4mas-sft-x5-single-ep3

SGLang

How to use yinita/ps4mas-sft-x5-single-ep3 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 "yinita/ps4mas-sft-x5-single-ep3" \
    --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": "yinita/ps4mas-sft-x5-single-ep3",
		"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 "yinita/ps4mas-sft-x5-single-ep3" \
        --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": "yinita/ps4mas-sft-x5-single-ep3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yinita/ps4mas-sft-x5-single-ep3 with Docker Model Runner:
```
docker model run hf.co/yinita/ps4mas-sft-x5-single-ep3
```

PS4MAS SFT full-FT — x5 single ep3 (best single / protocol)

Full fine-tune of Qwen/Qwen3.5-9B for PS4MAS (Personalized Safety for Multi-Agent Systems).

Local run: results/0617/sft_full_9b_claude_x5_single_ep3
HF repo: yinita/ps4mas-sft-x5-single-ep3
Teacher: Claude Sonnet (x5 Claude distillation data)
Eval: tiny_eval — 50 scenarios × 4 cold topologies (200 traces), judge = GPT-OSS-120B

tiny_eval results

Model	Method	Overall	Single	Central	Hier	Debate	avg_ask	zero_tool%
baseline_9b (Qwen3.5-9B)	raw	3.386	2.140	3.613	3.508	4.281	1.74	90.0
x5_mixed_ep1 (this / sibling)	SFT full-FT	3.679	2.387	4.101	3.821	4.407	1.95	48.0
x5_mixed_ep3 (bottom-line)	SFT full-FT	3.622	2.267	3.974	3.801	4.448	1.93	58.0
x5_single_ep3	SFT full-FT	3.646	2.600	3.821	3.881	4.281	2.13	6.0
ceod_gate_lr_sft_v1	SFT LoRA	3.602	2.326	4.094	3.747	4.241	1.89	58.0
low400_ep3 (weights not on disk)	SFT full-FT	3.682	2.546	3.854	3.860	4.467	1.86	66.0

Why this checkpoint

Best PS-cold-single among SFT full-FT (2.600) and dramatically lower single zero_tool rate (6% vs ~48–58% for mixed). Trained on single-topology Claude x5 data (3 epochs).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "yinita/ps4mas-sft-x5-single-ep3"
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(repo)

Citation / project

PS4MAS — Personalized Safety Multi-Agent Systems (internal research checkpoint).

Downloads last month: 35

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for yinita/ps4mas-sft-x5-single-ep3

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(533)

this model

Adapters

3 models