Text Generation
Transformers
Safetensors
English
Russian
qwen3_5
image-text-to-text
weight-space-programming
wspforge
math
experimental
conversational
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
- Transformers
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
Download wspforge/research_code/src/code_sandbox.py from end000/Qwen3.5-0.8B-WSPForge-Math-v1: direct link, hf CLI and curl.
- Browser
- Download file 3.4 kB
-
https://huggingface.co/end000/Qwen3.5-0.8B-WSPForge-Math-v1/resolve/main/wspforge/research_code/src/code_sandbox.py
- Command line
-
hf download hf://end000/Qwen3.5-0.8B-WSPForge-Math-v1/wspforge/research_code/src/code_sandbox.py
-
curl -L -o code_sandbox.py https://huggingface.co/end000/Qwen3.5-0.8B-WSPForge-Math-v1/resolve/main/wspforge/research_code/src/code_sandbox.py
3.4 kB
| import json | |
| import os | |
| import platform | |
| import resource | |
| import secrets | |
| import signal | |
| import struct | |
| import subprocess | |
| import tempfile | |
| from pathlib import Path | |
| from common import ROOT | |
| def seccomp_program(): | |
| if platform.machine() != 'x86_64': | |
| raise RuntimeError('Sandbox syscall profile requires x86_64') | |
| instructions = [(0x20,0,0,4),(0x15,1,0,0xc000003e),(0x06,0,0,0x80000000), | |
| (0x20,0,0,0),(0x45,0,1,0x40000000),(0x06,0,0,0x00050001)] | |
| for number in [41,42,43,44,45,46,47,49,50,53,56,57,58,101,165,166,272,288,298,304,308,310,311,321,323,428,429,430,431,432,435,442]: | |
| instructions += [(0x15,0,1,number),(0x06,0,0,0x00050001)] | |
| instructions.append((0x06,0,0,0x7fff0000)) | |
| return b''.join(struct.pack('HBBI',*instruction) for instruction in instructions) | |
| def limits(): | |
| resource.setrlimit(resource.RLIMIT_CPU,(2,2)) | |
| resource.setrlimit(resource.RLIMIT_AS,(384*1024**2,384*1024**2)) | |
| resource.setrlimit(resource.RLIMIT_FSIZE,(65536,65536)) | |
| resource.setrlimit(resource.RLIMIT_NOFILE,(64,64)) | |
| resource.setrlimit(resource.RLIMIT_CORE,(0,0)) | |
| def check_code(code,entry_point,test_code): | |
| base = ROOT/'tmp/coding_sandbox' | |
| base.mkdir(parents=True,exist_ok=True) | |
| nonce = secrets.token_hex(16) | |
| with tempfile.TemporaryDirectory(prefix='case-',dir=base) as directory: | |
| work = Path(directory) | |
| (work/'payload.json').write_text(json.dumps({'code':code,'entry_point':entry_point,'test_code':test_code})) | |
| (work/'worker.py').write_bytes((ROOT/'src/code_worker.py').read_bytes()) | |
| (work/'filter.bpf').write_bytes(seccomp_program()) | |
| with (work/'filter.bpf').open('rb') as filter_file, (work/'stdout.log').open('wb') as stdout, (work/'stderr.log').open('wb') as stderr: | |
| command = ['bwrap','--unshare-all','--die-with-parent','--new-session','--cap-drop','ALL', | |
| '--ro-bind','/usr','/usr','--symlink','usr/lib','/lib','--symlink','usr/lib64','/lib64', | |
| '--proc','/proc','--dev','/dev','--size','16777216','--tmpfs','/tmp', | |
| '--ro-bind',str(work),'/work','--chdir','/tmp','--clearenv','--setenv','PATH','/usr/bin', | |
| '--ro-bind',str(ROOT/'tools/python/cpython-3.12.13-linux-x86_64-gnu'),'/runtime', | |
| '--setenv','HOME','/tmp','--setenv','PYTHONHASHSEED','0','--seccomp',str(filter_file.fileno()), | |
| '/runtime/bin/python3.12','-I','-S','/work/worker.py',nonce] | |
| try: | |
| process = subprocess.run(command,stdout=stdout,stderr=stderr,timeout=4,pass_fds=(filter_file.fileno(),)) | |
| except subprocess.TimeoutExpired: | |
| return {'passed':False,'error_type':'Timeout','error':'wall_timeout_4s'} | |
| content = (work/'stdout.log').read_bytes()[:65536].decode(errors='replace') | |
| marker = '__WSP_RESULT__'+nonce | |
| matches = [line[len(marker):] for line in content.split('\n') if line.startswith(marker)] | |
| if process.returncode == 0 and len(matches)==1: | |
| return json.loads(matches[0]) | |
| error = (work/'stderr.log').read_bytes()[:1000].decode(errors='replace') | |
| if 'bwrap:' in error: | |
| raise RuntimeError('Sandbox infrastructure failure: '+error[:500]) | |
| return {'passed':False,'error_type':'ProcessFailure','returncode':process.returncode,'error':error[:300]} | |