Text Generation
Transformers
Safetensors
GGUF
English
qwen3_5
image-text-to-text
decision-model
typed-decisions
calibration
calibrated-probabilities
classification
tool-selection
agent-routing
decision-index
jevbench
jev-compatible
systemone
wald
wald-q4b
qwen3.5
4b
vllm
reasoning
llama.cpp
conversational
Eval Results (legacy)
Instructions to use org2ai/Wald-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use org2ai/Wald-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="org2ai/Wald-4B") 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("org2ai/Wald-4B") model = AutoModelForMultimodalLM.from_pretrained("org2ai/Wald-4B", 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 org2ai/Wald-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "org2ai/Wald-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "org2ai/Wald-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/org2ai/Wald-4B
- SGLang
How to use org2ai/Wald-4B 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 "org2ai/Wald-4B" \ --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": "org2ai/Wald-4B", "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 "org2ai/Wald-4B" \ --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": "org2ai/Wald-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use org2ai/Wald-4B with Docker Model Runner:
docker model run hf.co/org2ai/Wald-4B
org2ai
Wald-Q4B v2 (04701-c22 + Qwen3.5-4B vision tower): main = v2; v1.x at tags v1.2 / v1.2-main / v1.1 / v1.0
ef7481d Download evaluation/v2/code/di03_native_auto_engine.py from org2ai/Wald-4B: direct link, hf CLI and curl.
- Browser
- Download file 3.58 kB
-
https://huggingface.co/org2ai/Wald-4B/resolve/main/evaluation/v2/code/di03_native_auto_engine.py
- Command line
-
hf download hf://org2ai/Wald-4B/evaluation/v2/code/di03_native_auto_engine.py
-
curl -L -o di03_native_auto_engine.py https://huggingface.co/org2ai/Wald-4B/resolve/main/evaluation/v2/code/di03_native_auto_engine.py
3.58 kB
| """C16B native Auto 0.7 adapter for the official Decision Index Engine API. | |
| Uses the previously evaluated frozen native reader, not the released legacy | |
| plain/Reasoning server. Supplies only state/questions to inference. No launch, | |
| training, upload or power operations. Parallel-run timings are not leaderboard | |
| single-request latency measurements. | |
| """ | |
| import hashlib | |
| import importlib.util | |
| import time | |
| import json | |
| import sys | |
| from pathlib import Path | |
| from decision_index.engines.base import Engine, Unsupported, validate | |
| NATIVE_SHA = '764f3a683becd16b87b9ce9bfc01a5fe483ef26c9a3345a724b82780d73ea73a' | |
| MODEL_SHA = '2859df99ed481592cdc3731fd768bf29ccd63273b2dab623642ad3b38b0e14c4' | |
| class WaldNativeAuto(Engine): | |
| name = 'wald-v2-native-auto0.7' | |
| latency = 'Request wall time at declared concurrency; not official serial leaderboard latency.' | |
| def __init__(self, native_path, temperature_path, temperature_sha256, | |
| deadline_epoch, endpoint='http://127.0.0.1:8371', | |
| model='04400-c18', max_model_len=131072, reference_root=None, **options): | |
| super().__init__(**options) | |
| assert model == '04400-c18', 'This contract binds C16B only' | |
| path = Path(native_path) | |
| assert hashlib.sha256(path.read_bytes()).hexdigest() == NATIVE_SHA | |
| temp = Path(temperature_path) | |
| assert hashlib.sha256(temp.read_bytes()).hexdigest() == temperature_sha256 | |
| self.deadline_epoch = float(deadline_epoch) if deadline_epoch is not None else None | |
| assert self.deadline_epoch is None or self.deadline_epoch > time.time() | |
| if reference_root: | |
| root = Path(reference_root) | |
| pins = json.loads((root / 'source-pins.json').read_text())['files_sha256'] | |
| for rel, digest in pins.items(): | |
| assert hashlib.sha256((root / rel).read_bytes()).hexdigest() == digest | |
| if str(root) not in sys.path: | |
| sys.path.insert(0, str(root)) | |
| spec = importlib.util.spec_from_file_location('wald_frozen_native', path) | |
| self.native = importlib.util.module_from_spec(spec) | |
| spec.loader.exec_module(self.native) | |
| self.client, self.sov = self.native.make_client( | |
| endpoint, model, int(max_model_len), | |
| time.monotonic() + self.deadline_epoch - time.time() if self.deadline_epoch is not None else None) | |
| self.table = self.sov.load_tables(temp).get('A') | |
| self.model = model | |
| self.provenance = {'model': model, 'model_sha256': MODEL_SHA, | |
| 'native_reader_sha256': NATIVE_SHA, | |
| 'temperature_sha256': temperature_sha256, | |
| 'policy': 'native Auto 0.7; untempered A gate; at most 512 thought tokens; original option order', | |
| 'prompt_format': 'repeat_state_plain in native chat', | |
| 'wide': 'frozen onepass knockout; every supplied option receives probability', | |
| 'context_limit': int(max_model_len), 'no_truncation': True, | |
| 'new_training': False} | |
| def __call__(self, state, questions): | |
| if self.deadline_epoch is not None and time.time() >= self.deadline_epoch - 120: | |
| raise TimeoutError('Registered evaluation deadline reached') | |
| request = {'state': state, 'questions': questions} | |
| try: | |
| response = self.native.answer_task(self.client, self.sov, | |
| {'request': request, 'suite': 'di'}, self.table, 0.7, 512) | |
| except self.sov.Capacity as exc: | |
| raise Unsupported(str(exc)) from exc | |
| validate(questions, response) | |
| return response, response | |