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)

# 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=40)
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
```

jebadiah-9b-v2 / eval /config.json

jbrashear

Jebadiah 9B v2: merged bf16 weights, tokenizer, temperatures, scripts, eval records

b1d222a verified 9 days ago

Raw History Blame Contribute Delete

1.74 kB

	{
	"run_name": "9b-chat-v1",
	"description": "The v1 recipe on the CHAT checkpoint Qwen/Qwen3.5-9B (thinking off). 4b-chat-v1 scored 72.49 (best 4B ever, +2.2 over 4b-v1) with no synthetic data, so the base checkpoint is the lever. Read against 9b-v1 (73.29): the candidate for the published 9B v2.",
	"base_model": "Qwen/Qwen3.5-9B",
	"base_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a",
	"data_dir": "/workspace/jeb/data-v1",
	"dataset_path": "/workspace/jeb/data-v1/train.jsonl",
	"eval_dataset_path": "/workspace/jeb/data-v1/calib.jsonl",
	"output_dir": "/workspace/jeb/runs/9b-chat-v1",
	"method": "lora",
	"num_epochs": 1,
	"batch_size": 8,
	"gradient_accumulation_steps": 1,
	"learning_rate": 0.0001,
	"lr_scheduler_type": "cosine",
	"lora_rank": 16,
	"lora_alpha": 32,
	"max_seq_length": 2048,
	"warmup_steps": 30,
	"weight_decay": 0.0,
	"max_grad_norm": 1.0,
	"use_gradient_checkpointing": true,
	"attn_implementation": "sdpa",
	"eval_steps": 200,
	"logging_steps": 10,
	"seed": 17,
	"decide": {
	"objective": "candidate_ce",
	"shuffle_choice_options": true,
	"lora_dropout": 0.05,
	"calib_eval_limit": 358,
	"target_modules": "all-linear",
	"score_targets": "ordinal",
	"score_ordinal_adjacent": 0.2
	},
	"prompt_source_sha256": "d2660ebec28bd3f1704235bda88d24a397c1c62475e740519cb8ef2d08f25fdd",
	"prompt_source_commit": "e5c089386e0239c9eb270eeb490d181722b8da5b",
	"sweep": {
	"letter": "h",
	"smoke": false,
	"eval_only": false,
	"max_steps": -1,
	"eval_limit": 0,
	"eval_repeats": 5,
	"eval_repeats_for": "jevals-=5,nimble-eval=3,kev-transfer=3,typed-decisions=2,kev-decision=1,nimble-public=1",
	"eval_batch_size": 16,
	"eval_latency_sample": 30,
	"temperature_target": "train",
	"notes": []
	}
	}