Instructions to use jbrashear/Aegis-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jbrashear/Aegis-14B with Transformers:

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

pipe = pipeline("text-generation", model="jbrashear/Aegis-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jbrashear/Aegis-14B")
model = AutoModelForCausalLM.from_pretrained("jbrashear/Aegis-14B")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jbrashear/Aegis-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jbrashear/Aegis-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jbrashear/Aegis-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jbrashear/Aegis-14B

SGLang

How to use jbrashear/Aegis-14B 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 "jbrashear/Aegis-14B" \
    --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": "jbrashear/Aegis-14B",
		"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 "jbrashear/Aegis-14B" \
        --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": "jbrashear/Aegis-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jbrashear/Aegis-14B with Docker Model Runner:
```
docker model run hf.co/jbrashear/Aegis-14B
```

Aegis-14B

A governed dataset-refinery agent, fine-tuned from NousResearch/Hermes-4-14B (Qwen3-14B base) to power Aegis — a Conductor-governed autonomous dataset refinery that turns messy data into clean ShareGPT/ChatML training sets, with a human gate on every dollar the agent spends and a signed audit certificate.

Built for the Nous Research × NVIDIA × Stripe hackathon. Trained and quantized locally on a single NVIDIA DGX Spark (GB10).

Note: ~14.8B params (Hermes-4-14B base). The model's system prompt self-identifies as "Aegis-7B" (the project's early working name); the model and repo are Aegis-14B.

What it does

Given a data-refinement task it returns strict JSON for four jobs:

quality — assess a raw data sample's fitness for fine-tuning
triage — score a refinement job's complexity / risk
spend — propose (or, by default, reject in favor of local) a gated external-tool spend
audit — produce the decision trace for the signed certificate

It is trained to be conservative and local-first: it only proposes paid external work when local processing genuinely can't do the job, and never assumes spend approval.

Usage (OpenAI-compatible)

Serve with vLLM (on GB10, launch with --attention-backend TRITON_ATTN --enforce-eager). Send the Aegis system prompt as the system message; the model replies with JSON only. Use temperature=0 and response_format={"type":"json_object"}.

Training

LoRA (r=16, α=32) over 433 synthetic ShareGPT examples across the four jobs (balanced), 3 epochs, bf16, on one DGX Spark. Held-out eval (48): 100% valid JSON, 91% schema-correct.

License & credits

Derivative of NousResearch/Hermes-4-14B and inherits its license terms. Credit to Nous Research (Hermes 4) and the Qwen3 base. Built with AInode on NVIDIA DGX Spark.

Downloads last month: 29

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for jbrashear/Aegis-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

NousResearch/Hermes-4-14B

Adapter

(1)

this model

Adapters

2 models