Instructions to use quaedra/jet-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quaedra/jet-4b with Transformers:

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

pipe = pipeline("text-generation", model="quaedra/jet-4b")
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("quaedra/jet-4b")
model = AutoModelForCausalLM.from_pretrained("quaedra/jet-4b", 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 quaedra/jet-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quaedra/jet-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": "quaedra/jet-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/quaedra/jet-4b

SGLang

How to use quaedra/jet-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 "quaedra/jet-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": "quaedra/jet-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 "quaedra/jet-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": "quaedra/jet-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use quaedra/jet-4b with Docker Model Runner:
```
docker model run hf.co/quaedra/jet-4b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Jet-4B

v6.2.0 · released 2026-09-26 · focused continuation, selected step 250. Jet-4B, part of the Jet family, returns typed decisions and probabilities from supplied options without generating free-form answers. This is the full merged BF16 model, not an adapter, fine-tuned from Qwen3.5-4B. No separate base-model download is required. It replaces v6.1 in quaedra/jet-4b; previous releases remain accessible by their version tags.

Run

Linux + NVIDIA CUDA, Python 3.12. Verified with PyTorch 2.11.0+cu128, Transformers 5.17.0 and flash-linear-attention 0.5.2.

hf download quaedra/jet-4b --revision v6.2.0 --local-dir jet-4b
cd jet-4b
python -m pip install -r requirements.txt
python jet.py <<'JSON'
{"state":"I was charged twice this month.","questions":{"topic":{"type":"choice","instructions":"What is the primary issue?","criteria":{"billing":"billing or payment problem","bug":"the product is broken"}}}}
JSON

from jet import Jet
model = Jet()
result = model.decide("The item arrived broken.", {
    "damaged": {"type": "noul", "instructions": "Is the item damaged?"}
})

Type	Input	Output
`choice`	2–255 named options	Selected key and probabilities
`score`	2–10 ordered levels	Expected zero-based score, selected level, probabilities
`noul`	Yes/no question	Probability of yes

Use the included native prompt and restricted label-token readout. A generic text-generation pipeline does not implement this API. Questions are processed separately. The runtime now accepts complete prompts up to 16,384 tokens; inputs and options are never silently truncated. The longest reconstructed API-Bank input (11,495 tokens) passed the standalone runtime check, but full API-Bank accuracy has not been measured for this release. Context feasibility does not establish long-context quality across tasks.

FLA is enabled; convolution uses the PyTorch fallback. confidence is normalized inverse entropy, not a calibrated correctness probability. Temperatures are inherited from v6.1 and were not refitted or established as calibrated for v6.2.

Training and selection

The parent is full merged Jet-4B v6.1 at f446b82727be57da348bb46eccf211414294ab3e. Parent shard hashes and the exact adapter hash are in merge-provenance.json. A fresh rank/alpha-16 correction LoRA was trained on that parent; the model was not reset to the original Qwen weights.

4,000 examples: 800 banking intent, 800 entity-specific financial sentiment, 400 sarcasm/literal, and 2,000 broad retention examples.
BF16 backbone / FP32 adapter, dropout .05, microbatch 1, accumulation 4, seed 260925; two trials of 1,000 updates at peak learning rates 3e-6 and 8e-6.
Validation-selected winner: 3e-6 at step 250. The higher-rate trial failed the selection guards and is not included in this release.
Selection used 915 examples and an objective of 70% mean focus metrics plus 30% retention accuracy; every family must stay within two percentage points of its initial metric. The winner was frozen before final holdout evaluation.
Banking uses the training partition of BANKING77, financial supervision uses SEntFiN, and sarcasm uses author-labeled iSarcasm training examples. Financial headlines and tweet/rephrase groups stay in one split.

Full-model holdout results

The results below were re-measured on the full merged model, after BF16 rounding. Focus holdouts exclude the previous local input corpus listed in the data audit; retention is reused. Small sample sizes mean these modest differences do not establish statistical significance or broad benchmark improvement.

Holdout / metric	Cases	v6.1	v6.2 merged
Banking / accuracy	154	74.68%	74.68%
Entity sentiment / macro-F1	180	71.16%	71.21%
Sarcasm / positive-class F1	80	46.81%	50.00%
Retention / accuracy	500	93.40%	93.40%

Financial sentiment is a SEntFiN transfer holdout, not the FinEntity benchmark. Banking and sarcasm rows above are local source holdouts, not their public test benchmark scores. Exact content/group exclusions do not establish semantic or pretraining decontamination. Benchmarks informed training focus.

Decision Index 0.3 (official, 2026-10-07): 40.01, rank 52 of 113. Run by the index maintainers on the full suite (110,201 requests, 42 benchmarks; 243 requests exceed the 16,384-token prompt limit): public 42.17, same skills 40.93, new domains 34.46. Within the index's tie band of the other entries on the same 4B base. Strongest in Tools & Automation (62.9), weakest in Knowledge & Reasoning (25.4); 66.0% accurate at 80.1% mean confidence (ECE 0.141). Details · Leaderboard

The earlier 25-benchmark comparison belongs to the v6.1 candidate and must not be attributed to this release.

Merge verification

FP32 B@A corrections were added to the already merged parent and rounded to BF16. All 426 tensors loaded without missing, unexpected or mismatched keys; 248 modules received updates. Nine shards contain 8,411,510,272 parameter bytes.

On 157 fixed verification cases, 0 selected answers changed between the adapter and merged model. The largest probability difference was 4.76 percentage points.

These checks include choice, score, noul and a long API-Bank input. The full 914-case holdout passed the predeclared release guards. See evaluation.json, merge-validation.json and release-manifest.json. Merge equivalence is approximate.

Website · Docs · Source and experiment records · Training protocol · Release validation

Apache-2.0 model/runtime; source datasets retain their own licenses. Dataset rows are not redistributed here. Quality outside the evaluated domains is not established.