Instructions to use frontier-infra/jebadiah-9b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frontier-infra/jebadiah-9b-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="frontier-infra/jebadiah-9b-v2")
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("frontier-infra/jebadiah-9b-v2")
model = AutoModelForMultimodalLM.from_pretrained("frontier-infra/jebadiah-9b-v2", 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 frontier-infra/jebadiah-9b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frontier-infra/jebadiah-9b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontier-infra/jebadiah-9b-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/frontier-infra/jebadiah-9b-v2

SGLang

How to use frontier-infra/jebadiah-9b-v2 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 "frontier-infra/jebadiah-9b-v2" \
    --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": "frontier-infra/jebadiah-9b-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "frontier-infra/jebadiah-9b-v2" \
        --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": "frontier-infra/jebadiah-9b-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use frontier-infra/jebadiah-9b-v2 with Docker Model Runner:
```
docker model run hf.co/frontier-infra/jebadiah-9b-v2
```

jbrashear commited on 9 days ago

Commit

071adba

verified ·

1 Parent(s): 5f73fe5

Model card: results links and community quants

Browse files

Files changed (1) hide show

README.md +19 -0

README.md CHANGED Viewed

@@ -73,6 +73,16 @@ This repository holds full bf16 weights: the v2 LoRA merged into `Qwen/Qwen3.5-9
 Made in Texas.
 ## Results
 Measured by us with AINode's bench, one logit read per question, the same rendered prompt for every model. Accuracy is the share of questions whose top label is the human label. Headline is the macro over the zero-shot public sets. These are our numbers on the public suites, not rows on the Jevals board.
@@ -148,6 +158,15 @@ Then send the same body to `https://<your-ainode>/v1/systemone` with `"model": "
 - **GGUF** for llama.cpp: [jebadiah-9b-v2-GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF). Same answer as these weights on 257 of 260 held-out questions (Q8_0) and 240 of 260 (Q4_K_M).
 - **MLX** for Apple silicon: [jebadiah-9b-v2-MLX](https://huggingface.co/frontier-infra/jebadiah-9b-v2-MLX). Same answer on 256 of 260 (8-bit; the 4-bit build fell under 90% and was not published).
 ## How it decides
 The prompt is AINode's own decide rendering (source commit `e5c08938`, hash in `prompt_contract.json`), through the chat template with thinking off. The option labels are single tokens; the answer is the distribution over those label tokens at the last prompt position, read in fp32 and temperature scaled per type (`temperatures.json`: choice 1.19, noul 1.09, score 1.22). Nothing is generated. Those are the `train` fit, which minimises NLL against the soft or ordinal target the model was taught; it softens, and it costs some ECE against hard labels on the calibration split. A sharper `hard` fit (0.79 / 0.67 / 0.83) is in the same file for a consumer who gates on the argmax. Thresholds belong to the caller: act on a high probability, confirm or escalate on a middle one, hand a low one to a person or a bigger model. The model never refuses.

 Made in Texas.
+**Results and docs**
+- Project site, with every result and how to run the models: [jebadiah.ai](https://jebadiah.ai).
+- JevBench v1.4.2: on its 231 public items, run through its own harness, Jebadiah 9B v2 scores 0.818 (Jebadiah 27B: 0.866, the same as Jev 1.13.0). This is my own run on the public items, not the official board, which also uses sealed items. [Details and caveats](https://github.com/getainode/jebadiah#where-we-stand-on-jevbench).
+- [JDE](https://github.com/Titanium-Devops/jde) blind test (as of 2026-09-26): on 290 real decisions from Titanium Computing's production decision engine, Jebadiah 9B v2 got 277 against Jev's 282, with 0 flips across 5,800 repeat calls. Jev still leads on coverage checks.
+- For the family: [Decision Index 0.2.1](https://huggingface.co/spaces/multimodalart/jev-decision-index): the 27B scores 54.67, #5 of 67 open models (as of 2026-09-26). This is the board's own number; the maintainer validated my run and put it on the leaderboard. [Run record](https://huggingface.co/datasets/frontier-infra/jebadiah-decision-index-results/tree/main/runs/jebadiah-27b-1c0d794f).
+- All sizes: the [Hugging Face collection](https://huggingface.co/collections/frontier-infra/jebadiah-open-system-one-decision-models-6ab80765ddd3fa0b3eba5213), mirrored on [ModelScope](https://www.modelscope.ai/profile/JasonBrashear).
+**Which one should I use?** For local use, start with [Jebadiah 9B v2 GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF). On Apple silicon, use an MLX build: [27B](https://huggingface.co/frontier-infra/jebadiah-27b-MLX), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2-MLX) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2-MLX). For vLLM or fine-tuning, use the full weights: [27B](https://huggingface.co/frontier-infra/jebadiah-27b), [9B v2](https://huggingface.co/frontier-infra/jebadiah-9b-v2) or [4B v2](https://huggingface.co/frontier-infra/jebadiah-4b-v2).
 ## Results
 Measured by us with AINode's bench, one logit read per question, the same rendered prompt for every model. Accuracy is the share of questions whose top label is the human label. Headline is the macro over the zero-shot public sets. These are our numbers on the public suites, not rows on the Jevals board.
 - **GGUF** for llama.cpp: [jebadiah-9b-v2-GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF). Same answer as these weights on 257 of 260 held-out questions (Q8_0) and 240 of 260 (Q4_K_M).
 - **MLX** for Apple silicon: [jebadiah-9b-v2-MLX](https://huggingface.co/frontier-infra/jebadiah-9b-v2-MLX). Same answer on 256 of 260 (8-bit; the 4-bit build fell under 90% and was not published).
+## Community quantizations
+Thanks to bartowski and mradermacher for building GGUF quantizations of this model:
+- [bartowski/frontier-infra_jebadiah-9b-v2-GGUF](https://huggingface.co/bartowski/frontier-infra_jebadiah-9b-v2-GGUF)
+- [mradermacher/jebadiah-9b-v2-GGUF](https://huggingface.co/mradermacher/jebadiah-9b-v2-GGUF)
+These are independent builds. The agreement numbers under Other formats are for my builds in [jebadiah-9b-v2-GGUF](https://huggingface.co/frontier-infra/jebadiah-9b-v2-GGUF), not for these.
 ## How it decides
 The prompt is AINode's own decide rendering (source commit `e5c08938`, hash in `prompt_contract.json`), through the chat template with thinking off. The option labels are single tokens; the answer is the distribution over those label tokens at the last prompt position, read in fp32 and temperature scaled per type (`temperatures.json`: choice 1.19, noul 1.09, score 1.22). Nothing is generated. Those are the `train` fit, which minimises NLL against the soft or ordinal target the model was taught; it softens, and it costs some ECE against hard labels on the calibration split. A sharper `hard` fit (0.79 / 0.67 / 0.83) is in the same file for a consumer who gates on the argmax. Thresholds belong to the caller: act on a high probability, confirm or escalate on a middle one, hand a low one to a person or a bigger model. The model never refuses.