Instructions to use CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915 with Transformers:

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

pipe = pipeline("text-generation", model="CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915")
model = AutoModelForCausalLM.from_pretrained("CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915", 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 CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915

SGLang

How to use CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915 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 "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915" \
    --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": "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915",
		"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 "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915" \
        --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": "CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915 with Docker Model Runner:
```
docker model run hf.co/CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915
```

Qwen3-4B BrowseComp Worker SFT (0915)

Final full-parameter SFT worker checkpoint iter_1366, trained on four NVIDIA GB300 GPUs using Miles. No RL has been applied. Intended as a research worker under a frozen, self-hosted MiniMax-M2.7 coordinator.

Code and reproduction: Miles, paper/browsecomp-4b-training-nvidia-b300-0915.

Evaluation

One full round on the same frozen 150-question BrowseComp-Plus/FoldAgent test split, using MiniMax-M2.7 coordinator, hybrid BM25+dense RRF retrieval and Gemini 3.6 Flash grading. Runtime STOP gate is off.

Worker	Easy	Medium	Hard	Total
Original Qwen3-4B	43/50	29/50	11/50	83/150 (55.33%)
This SFT model	49/50	41/50	18/50	108/150 (72.00%)

Paired improvement: 31 questions improved, 6 regressed, +16.67 percentage points. SFT accuracy Wilson 95% interval: 64.33–78.57%. These are system scores with the coordinator and retrieval, not standalone model scores. This is a single stochastic round, not pass@k. Budget-exhausted episodes remain in the denominator.

Training

Initialization: Qwen/Qwen3-4B revision 1cfa9a7208912126459214e8b04321603b3df60c (pretrained/instruction model, not random initialization).
Core: Shangy/browsecomp-worker-sft revision f1f0fb3053ef0cd15831a58e7943901340666630, data/core.jsonl, 541 trajectories repeated 3 times.
Gate: Shangy/browsecomp-worker-gate-sft-v1 revision eb62ff5f74592b3409488fb52281d94ab3c5f22d, gating/train.jsonl, 18,698 source rows (already includes hard-negative repeats).
Balance by exact Miles Qwen3 supervised token masks: 1,623 core rows + 42,137 sampled gate rows = 43,760 rows, 3,952,827 worker vs 3,952,818 gate supervised tokens. Seed 42.
No 904-row worker replay, no mix.jsonl, no gate validation/holdout included.
Adam, LR 1e-5, cosine to 1e-6, warmup 10%, weight decay 0.1, beta=(0.9,0.95), batch 32, TP4, context 40,960, full recomputation, one constructed-mixture epoch.
Miles uses floor division for epoch length: 1,367 rollout slots; release-checkpoint initialization starts at rollout 1, ending at 1,366. See run metadata for actual updates.
Training template: miles/utils/chat_template_utils/templates/qwen3_fixed.jinja; assistant-only loss.

Serving

Use the same evaluation keep-thinking template as the raw baseline: examples/browsecomp/gb300_main_eval_0907/templates/qwen3_fixed_keepthink.jinja in the linked repository. SGLang: TP1 per worker, context 40,960; worker episode budget 24,576 tokens, up to 40 turns, max 4,096 generated tokens per turn, temperature 1, top-p .95. The model emits the BrowseComp XML-style search, open_page, and finish calls; use the repository's worker prompts and environment.

This repository contains the exact serving variant used for the SFT evaluation: 128 vocabulary-padding rows removed from the exported embedding, all original vocabulary rows retained byte-for-byte. Tokenizer files are restored from the pinned original Qwen3-4B; export reserialization changed defaults but preserved vocabulary, merges and added tokens. The original training export is retained in the experiment workspace.

Limitations

Core exports lack parent-question IDs, so question-level test exclusion cannot be independently proven from that file. Gate question hashes were checked: all originate from the 680-question training split, with disjoint train/validation/holdout and no overlap with the 150 test questions. This checkpoint should not be described as a proven contamination-free benchmark model.

The documented historical 8B SFT mixture was adapted to 4B with exact current loss-mask token balancing; it is not a byte-identical reproduction of the historical mixer. Model weight-content hashes are published in SHA256SUMS.

Downloads last month: 195

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for CharlieLLL/Qwen3-4B-BrowseComp-Worker-SFT-0915

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1045)

this model

Finetunes

2 models