Instructions to use org2ai/Wald-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

Wald-4B / temperature.json

Harry19081

Release Wald-Q4B22D0-f7: full DI0.2.1 54.59 and clean calibration

503dfd6 verified 13 days ago

Raw History Blame

4.35 kB

	{
	"A": {
	"single": 1.3660402567543957,
	"buckets": {
	"choice\|2": {
	"temperature": 1.189207115002721,
	"n": 36,
	"fitted": true
	},
	"choice\|3-4": {
	"temperature": 1.741101126592248,
	"n": 59,
	"fitted": true
	},
	"choice\|5-8": {
	"temperature": 1.3660402567543957,
	"n": 17,
	"fitted": false
	},
	"choice\|9+": {
	"temperature": 1.0717734625362931,
	"n": 27,
	"fitted": true
	},
	"noul\|2": {
	"temperature": 1.319507910772894,
	"n": 99,
	"fitted": true
	},
	"score\|5-8": {
	"temperature": 1.3660402567543957,
	"n": 18,
	"fitted": false
	}
	},
	"min_rows": 20,
	"rows": 256,
	"readout": "A",
	"fit": "min micro mean NLL over a 161-point log grid 0.25..64, per (type, option-count bucket); buckets with fewer than 20 rows use `single`"
	},
	"B256": {
	"single": 1.5157165665103978,
	"buckets": {
	"choice\|2": {
	"temperature": 1.8660659830736155,
	"n": 36,
	"fitted": true
	},
	"choice\|3-4": {
	"temperature": 1.8025009252216606,
	"n": 59,
	"fitted": true
	},
	"choice\|5-8": {
	"temperature": 1.5157165665103978,
	"n": 17,
	"fitted": false
	},
	"choice\|9+": {
	"temperature": 1.109569472067845,
	"n": 27,
	"fitted": true
	},
	"noul\|2": {
	"temperature": 1.4142135623730951,
	"n": 99,
	"fitted": true
	},
	"score\|5-8": {
	"temperature": 1.5157165665103978,
	"n": 18,
	"fitted": false
	}
	},
	"min_rows": 20,
	"rows": 256,
	"readout": "B256",
	"fit": "min micro mean NLL over a 161-point log grid 0.25..64, per (type, option-count bucket); buckets with fewer than 20 rows use `single`"
	},
	"B512": {
	"single": 1.5691681957935015,
	"buckets": {
	"choice\|2": {
	"temperature": 1.9999999999999998,
	"n": 36,
	"fitted": true
	},
	"choice\|3-4": {
	"temperature": 1.8660659830736155,
	"n": 59,
	"fitted": true
	},
	"choice\|5-8": {
	"temperature": 1.5691681957935015,
	"n": 17,
	"fitted": false
	},
	"choice\|9+": {
	"temperature": 1.0352649238413776,
	"n": 27,
	"fitted": true
	},
	"noul\|2": {
	"temperature": 1.5157165665103978,
	"n": 99,
	"fitted": true
	},
	"score\|5-8": {
	"temperature": 1.5691681957935015,
	"n": 18,
	"fitted": false
	}
	},
	"min_rows": 20,
	"rows": 256,
	"readout": "B512",
	"fit": "min micro mean NLL over a 161-point log grid 0.25..64, per (type, option-count bucket); buckets with fewer than 20 rows use `single`"
	},
	"B": {
	"single": 1.5691681957935015,
	"buckets": {
	"choice\|2": {
	"temperature": 1.9999999999999998,
	"n": 36,
	"fitted": true
	},
	"choice\|3-4": {
	"temperature": 1.8660659830736155,
	"n": 59,
	"fitted": true
	},
	"choice\|5-8": {
	"temperature": 1.5691681957935015,
	"n": 17,
	"fitted": false
	},
	"choice\|9+": {
	"temperature": 1.0352649238413776,
	"n": 27,
	"fitted": true
	},
	"noul\|2": {
	"temperature": 1.5157165665103978,
	"n": 99,
	"fitted": true
	},
	"score\|5-8": {
	"temperature": 1.5691681957935015,
	"n": 18,
	"fitted": false
	}
	},
	"min_rows": 20,
	"rows": 256,
	"readout": "B512",
	"fit": "min micro mean NLL over a 161-point log grid 0.25..64, per (type, option-count bucket); buckets with fewer than 20 rows use `single`"
	},
	"provenance": {
	"model": "022D0-f7 merged",
	"fit_source": "XL-dev calibration only",
	"raw_output_sha256": "4af949176c1348f2bb9822ee6b309274c4e774e9581a26a031e37095dc468b3a",
	"source_items_sha256": "ee2e8db4eed8112e629e8b7192d46efc9e9f5eb7b8d21cdd172396e0457a22c0",
	"known_di_matches_excluded": 19,
	"additional_hle_matches_excluded": 0,
	"calibration_rows": 256,
	"b_mode": "B512",
	"method": "eval.distill_eval.fit_table micro NLL; no model weight changes; no DI labels or scores used"
	}
	}