Instructions to use end000/Qwen3.5-0.8B-WSPForge-Math-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use end000/Qwen3.5-0.8B-WSPForge-Math-v1 with Transformers:

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

pipe = pipeline("text-generation", model="end000/Qwen3.5-0.8B-WSPForge-Math-v1")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("end000/Qwen3.5-0.8B-WSPForge-Math-v1")
model = AutoModelForMultimodalLM.from_pretrained("end000/Qwen3.5-0.8B-WSPForge-Math-v1", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use end000/Qwen3.5-0.8B-WSPForge-Math-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "end000/Qwen3.5-0.8B-WSPForge-Math-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "end000/Qwen3.5-0.8B-WSPForge-Math-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/end000/Qwen3.5-0.8B-WSPForge-Math-v1

SGLang

How to use end000/Qwen3.5-0.8B-WSPForge-Math-v1 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 "end000/Qwen3.5-0.8B-WSPForge-Math-v1" \
    --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": "end000/Qwen3.5-0.8B-WSPForge-Math-v1",
		"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 "end000/Qwen3.5-0.8B-WSPForge-Math-v1" \
        --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": "end000/Qwen3.5-0.8B-WSPForge-Math-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use end000/Qwen3.5-0.8B-WSPForge-Math-v1 with Docker Model Runner:
```
docker model run hf.co/end000/Qwen3.5-0.8B-WSPForge-Math-v1
```

Qwen3.5-0.8B-WSPForge-Math-v1 / wspforge /research_code /scripts /prepare_data.py

end000

Release Sol014 mathematical specialization with paired evaluations, regressions and exact replay artifacts

fc32096 verified about 21 hours ago

Raw History Blame Contribute Delete

2.63 kB

import hashlib
import json
from pathlib import Path
import shutil
import urllib.request
from datasets import load_dataset
from common import ROOT, save_json


def dump(path, items):
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(''.join(json.dumps(x, ensure_ascii=False) + '\n' for x in items))


def main():
    practice = ROOT / 'data/practice'
    practice.mkdir(exist_ok=True)
    for f in (ROOT / 'sources/lm_understand-logs/exp8_math/practice').glob('*.jsonl'):
        shutil.copyfile(f, practice / f.name)
    manifest = []
    specs = [('HuggingFaceH4/MATH-500', None, 'math500'), ('openai/gsm8k', 'main', 'gsm8k')]
    for repo, config, name in specs:
        with urllib.request.urlopen(f'https://huggingface.co/api/datasets/{repo}') as response:
            revision = json.load(response)['sha']
        ds = load_dataset(repo, config, split='test', revision=revision)
        if name == 'math500':
            items = [{'id': r['unique_id'], 'problem': r['problem'], 'answer': r['answer']} for r in ds]
        else:
            items = [{'id': f'gsm8k_test_{i}', 'problem': r['question'], 'answer': r['answer'].split('####')[-1].strip().replace(',', '')} for i, r in enumerate(ds)]
        path = ROOT / f'data/locked_test/{name}.jsonl'
        dump(path, items)
        manifest.append({'repo': repo, 'revision': revision, 'rows': len(items), 'sha256': hashlib.sha256(path.read_bytes()).hexdigest()})
    with urllib.request.urlopen('https://api.github.com/repos/google-research/google-research/commits/master') as response:
        revision = json.load(response)['sha']
    target = ROOT / 'sources/instruction_following_eval'
    target.mkdir(exist_ok=True)
    for name in ('instructions.py', 'instructions_registry.py', 'instructions_util.py', 'evaluation_lib.py', 'data/input_data.jsonl'):
        with urllib.request.urlopen(f'https://raw.githubusercontent.com/google-research/google-research/{revision}/instruction_following_eval/{name}') as response:
            content = response.read()
        out = ROOT / 'data/locked_test/ifeval.jsonl' if name.startswith('data/') else target / name
        out.write_bytes(content)
    (target / '__init__.py').touch()
    manifest.append({'repo': 'google-research/google-research', 'revision': revision, 'path': 'instruction_following_eval'})
    save_json(ROOT / 'data/provenance.json', manifest)
    from split_data import main as split_data
    split_data()
    print('Данные скачаны, исследовательские и отложенные выборки разделены.')


if __name__ == '__main__':
    main()

	import hashlib
	import json
	from pathlib import Path
	import shutil
	import urllib.request
	from datasets import load_dataset
	from common import ROOT, save_json


	def dump(path, items):
	path.parent.mkdir(parents=True, exist_ok=True)
	path.write_text(''.join(json.dumps(x, ensure_ascii=False) + '\n' for x in items))


	def main():
	practice = ROOT / 'data/practice'
	practice.mkdir(exist_ok=True)
	for f in (ROOT / 'sources/lm_understand-logs/exp8_math/practice').glob('*.jsonl'):
	shutil.copyfile(f, practice / f.name)
	manifest = []
	specs = [('HuggingFaceH4/MATH-500', None, 'math500'), ('openai/gsm8k', 'main', 'gsm8k')]
	for repo, config, name in specs:
	with urllib.request.urlopen(f'https://huggingface.co/api/datasets/{repo}') as response:
	revision = json.load(response)['sha']
	ds = load_dataset(repo, config, split='test', revision=revision)
	if name == 'math500':
	items = [{'id': r['unique_id'], 'problem': r['problem'], 'answer': r['answer']} for r in ds]
	else:
	items = [{'id': f'gsm8k_test_{i}', 'problem': r['question'], 'answer': r['answer'].split('####')[-1].strip().replace(',', '')} for i, r in enumerate(ds)]
	path = ROOT / f'data/locked_test/{name}.jsonl'
	dump(path, items)
	manifest.append({'repo': repo, 'revision': revision, 'rows': len(items), 'sha256': hashlib.sha256(path.read_bytes()).hexdigest()})
	with urllib.request.urlopen('https://api.github.com/repos/google-research/google-research/commits/master') as response:
	revision = json.load(response)['sha']
	target = ROOT / 'sources/instruction_following_eval'
	target.mkdir(exist_ok=True)
	for name in ('instructions.py', 'instructions_registry.py', 'instructions_util.py', 'evaluation_lib.py', 'data/input_data.jsonl'):
	with urllib.request.urlopen(f'https://raw.githubusercontent.com/google-research/google-research/{revision}/instruction_following_eval/{name}') as response:
	content = response.read()
	out = ROOT / 'data/locked_test/ifeval.jsonl' if name.startswith('data/') else target / name
	out.write_bytes(content)
	(target / '__init__.py').touch()
	manifest.append({'repo': 'google-research/google-research', 'revision': revision, 'path': 'instruction_following_eval'})
	save_json(ROOT / 'data/provenance.json', manifest)
	from split_data import main as split_data
	split_data()
	print('Данные скачаны, исследовательские и отложенные выборки разделены.')


	if __name__ == '__main__':
	main()