Instructions to use PromptExecutionAU/wattson-granite-4.2-8b-py with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PromptExecutionAU/wattson-granite-4.2-8b-py with Transformers:

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

pipe = pipeline("text-generation", model="PromptExecutionAU/wattson-granite-4.2-8b-py")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PromptExecutionAU/wattson-granite-4.2-8b-py")
model = AutoModelForCausalLM.from_pretrained("PromptExecutionAU/wattson-granite-4.2-8b-py", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PromptExecutionAU/wattson-granite-4.2-8b-py with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PromptExecutionAU/wattson-granite-4.2-8b-py"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PromptExecutionAU/wattson-granite-4.2-8b-py",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PromptExecutionAU/wattson-granite-4.2-8b-py

SGLang

How to use PromptExecutionAU/wattson-granite-4.2-8b-py 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 "PromptExecutionAU/wattson-granite-4.2-8b-py" \
    --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": "PromptExecutionAU/wattson-granite-4.2-8b-py",
		"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 "PromptExecutionAU/wattson-granite-4.2-8b-py" \
        --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": "PromptExecutionAU/wattson-granite-4.2-8b-py",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PromptExecutionAU/wattson-granite-4.2-8b-py with Docker Model Runner:
```
docker model run hf.co/PromptExecutionAU/wattson-granite-4.2-8b-py
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

wattson-granite-4.2-8b-py

Granite 4.2 8B fine-tuned (LoRA, merged to bf16) to answer AC power-flow questions about transmission networks by writing Python that calls a solver, and never computing numbers itself. Part of WattsOn / wattson.

What it does

It is given a run_python tool (a restricted Python shell with a solver module: solver.trial(...) runs a pandapower AC power flow, solver.exists(...) checks that a line or bus exists) and tasks such as fitting a load scale to a voltage target, reporting an N-1 contingency, choosing the worst of several outages, or refusing a task that names an element that does not exist.

Evaluation (held-out networks, one seed)

Suite	Result
Held-out fits and reports (90)	90 of 90
Smoke (20)	20 of 20
Judgement: worst outage (40)	36 of 40
Unsolvable: must refuse (28)	14 of 28
Planning: multi-candidate (40)	40 of 40
Held-out attempts containing a number no tool or prompt gave the model	0 of 90
Derived-arithmetic suite (40)	37 of 40
Derived-suite attempts containing a number no tool or prompt gave the model	0 of 40 (the exposure measure flags 1: the model computed a mean in Python, printed `mean88.69`, and copied it; the measure does not read a number glued to a word, so that flag is an artifact)

One training seed. The Qwen3.5-4B students of the same recipe vary by up to 9 tasks between seeds on the unsolvable suite, so the unsolvable score here should not be read as stable. Full tables and limits: docs/results.md in the repository.

Training

Base: ibm-granite/granite-4.2-8b at revision b3791992239dce12d0038f1f54a8adb7b02d59ab (Apache-2.0).
Data: 826 oracle-scripted trajectories (the programs, tool replies and answers are produced by a deterministic script that runs the real solver; no model-generated text). Networks: CSIRO Synthetic-NEM-2000-Bus (CC BY 4.0, CSIRO) and pandapower cases. Held-out evaluation networks are not in the training rows.
LoRA r=32, alpha=64, all attention and MLP projections; 2 epochs; learning rate 1e-4 cosine; sequence length 8192; seed 42.
Weight integrity: SHA-256 of every file is listed in hash_manifest.json in this repository.

Intended use and limits

For the WattsOn evaluation harness and research on tool-grounded numerical reasoning. It is not a power-system engineering tool and its answers must not be used for operational decisions.
The Python shell it calls is not a security boundary: it is a restricted python -I child with a module allowlist, a wall-clock limit and a memory limit. Do not expose it to untrusted input.
Evaluated on AC power flow only, on a handful of networks. Refusal of non-existent elements is the weakest behaviour.

Downloads last month: 331

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for PromptExecutionAU/wattson-granite-4.2-8b-py

Base model

ibm-granite/granite-4.1-8b-base

Finetuned

ibm-granite/granite-4.2-8b

Finetuned

(19)

this model

Quantizations

1 model