Instructions to use willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau with Transformers:

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

pipe = pipeline("text-generation", model="willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau")
model = AutoModelForCausalLM.from_pretrained("willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau", 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 willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau

SGLang

How to use willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau 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 "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau" \
    --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": "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau",
		"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 "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau" \
        --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": "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau with Docker Model Runner:
```
docker model run hf.co/willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau
```

Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau

An 8B agentic model trained with Entropy-Aware On-Policy Distillation (EOPD) in a multi-stage RL pipeline, built on Qwen3-8B-Base. This checkpoint is the final iteration (iter_0000300) of the Search-domain EOPD run.

Training pipeline

Stage	Description
Base	`Qwen/Qwen3-8B-Base`
SFT	Math + Search cold-start SFT, then Tau (tool-agent) SFT — student init `Qwen3-8B-Base-Math-SeaSFT-Search-TauSFT-Tau`
EOPD	On-policy distillation from a Search specialist teacher (`Qwen3-8B-Base-Math-SeaSFT-Search`)

Method: Entropy-Aware On-Policy Distillation (EOPD)

EOPD combines two KL directions to get the best of mode-seeking and mode-covering distillation:

Reverse-KL OPD everywhere (mode-seeking): the sampled-token log-ratio student_logp − teacher_logp is subtracted from the advantage, sharpening the student toward the teacher's modes.
Forward-KL on high-entropy teacher tokens (mode-covering): where reverse KL alone collapses diversity, a differentiable forward-KL loss KL(p̃_teacher_topk ‖ p̃_student_topk) is added, gated by the teacher's per-token entropy (1[H_teacher > τ]) and computed over the teacher's renormalized top-k (k=16) distribution.

The teacher is served with SGLang and returns both the scalar sampled-token logprob (reverse KL) and the per-token top-k distribution + entropy (forward KL). Training was done with the slime RL framework on Megatron-LM; this repo is the Hugging Face safetensors export of the final checkpoint.

Architecture

Identical to Qwen3-8B-Base: 36 layers, hidden size 4096, 32 attention heads, 8 KV heads (GQA), head dim 128, QK-LayerNorm, RMSNorm, SwiGLU, RoPE (θ=1e6), 151,936 vocab, 32,768 context.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")

prompt = "Who won the Nobel Prize in Physics in 1921?"
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=256)
print(tok.decode(out[0], skip_special_tokens=True))

The model is trained for a search/tool-use agent loop (Search-R1 style retrieval); to reproduce the agentic behavior, drive it with the same tool prompt/format used during training.

License

Apache-2.0, inherited from Qwen3-8B-Base.

Downloads last month: 326

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for willhx/Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau

Base model

Qwen/Qwen3-8B-Base

Finetuned

(500)

this model