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 /src /kernel.py

end000

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

fc32096 verified 1 day ago

Raw History Blame Contribute Delete

1.59 kB

import json
from pathlib import Path
import torch
from transformers import AutoTokenizer
from safetensors import safe_open
from common import ROOT, permit_compute, append
from weights import headers, load as read_weight, save_edit as write_edit

permit_compute()
torch.set_grad_enabled(False)
MODEL = ROOT / 'models/original'
CURRENT = ROOT / 'edits/current'
NAMES = sorted(headers(MODEL))
tok = AutoTokenizer.from_pretrained(MODEL, local_files_only=True)


def load_original(name):
    return read_weight(MODEL, name).float()


def load(name):
    if name not in NAMES:
        raise KeyError(name)
    path = CURRENT / (name + '.safetensors')
    if path.exists():
        with safe_open(str(path), framework='pt', device='cpu') as f:
            return f.get_tensor(name).float()
    return load_original(name)


def save_edit(name, tensor, hypothesis):
    return write_edit(MODEL, CURRENT, name, tensor, hypothesis)


def edited():
    return sorted(p.name.removesuffix('.safetensors') for p in CURRENT.glob('*.safetensors'))


def drop_edit(name):
    permit_compute()
    if name not in NAMES:
        raise KeyError(name)
    for suffix in ('.safetensors', '.json', '.analysis.json', '.direction.npy'):
        path = CURRENT / (name + suffix)
        if path.exists():
            path.unlink()
    append(ROOT / 'logs/experiments.jsonl', {'action': 'drop_edit', 'tensor': name})


print('CPU kernel готов: NAMES, load, load_original, save_edit(name,tensor,hypothesis), drop_edit, edited, tok. Градиенты отключены. Модель не запущена.')

	import json
	from pathlib import Path
	import torch
	from transformers import AutoTokenizer
	from safetensors import safe_open
	from common import ROOT, permit_compute, append
	from weights import headers, load as read_weight, save_edit as write_edit

	permit_compute()
	torch.set_grad_enabled(False)
	MODEL = ROOT / 'models/original'
	CURRENT = ROOT / 'edits/current'
	NAMES = sorted(headers(MODEL))
	tok = AutoTokenizer.from_pretrained(MODEL, local_files_only=True)


	def load_original(name):
	return read_weight(MODEL, name).float()


	def load(name):
	if name not in NAMES:
	raise KeyError(name)
	path = CURRENT / (name + '.safetensors')
	if path.exists():
	with safe_open(str(path), framework='pt', device='cpu') as f:
	return f.get_tensor(name).float()
	return load_original(name)


	def save_edit(name, tensor, hypothesis):
	return write_edit(MODEL, CURRENT, name, tensor, hypothesis)


	def edited():
	return sorted(p.name.removesuffix('.safetensors') for p in CURRENT.glob('*.safetensors'))


	def drop_edit(name):
	permit_compute()
	if name not in NAMES:
	raise KeyError(name)
	for suffix in ('.safetensors', '.json', '.analysis.json', '.direction.npy'):
	path = CURRENT / (name + suffix)
	if path.exists():
	path.unlink()
	append(ROOT / 'logs/experiments.jsonl', {'action': 'drop_edit', 'tensor': name})


	print('CPU kernel готов: NAMES, load, load_original, save_edit(name,tensor,hypothesis), drop_edit, edited, tok. Градиенты отключены. Модель не запущена.')