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
```

Results on a Brazilian Portuguese typed-decision benchmark

by ajgcvm - opened 3 days ago

Discussion

ajgcvm

3 days ago

Hi! We ran Jet v6.2 on a PT-BR typed-decisions benchmark: 7 tasks over native Brazilian Portuguese text, plus a held-out Central Bank FAQ task. We ran your Jet class unchanged, behind a minimal /v1/systemone wrapper. It scored 63.2% mean balanced accuracy, tied for second among the 13 untuned open decision models up to 4B we tested, and 97.6% on the FAQ task. A 4B fine-tuned on Portuguese reached 72.9% on the benchmark.

Full table and per-task results: https://huggingface.co/datasets/felhen-ai/ptbr-typed-decisions-bench
Evaluator: https://github.com/felhen-ai/saracura/blob/main/research/eval_http.py

If anything looks off for your model, like settings or server flags, tell us and we will rerun it. Thanks for releasing the weights.

michaljach changed discussion status to closed 2 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment