Instructions to use quaedra/jet-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Download evaluation.json from quaedra/jet-4b: direct link, hf CLI and curl.
- Browser
- Download file 3.37 kB
-
https://huggingface.co/quaedra/jet-4b/resolve/main/evaluation.json
- Command line
-
hf download hf://quaedra/jet-4b/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/quaedra/jet-4b/resolve/main/evaluation.json
3.37 kB
| { | |
| "scope": "914 fixed local holdout examples; new focus splits and reused retention split. Not official Decision Index scores.", | |
| "evaluated_format": "Full merged BF16 release, using native label-token argmax", | |
| "base_revision": "f446b82727be57da348bb46eccf211414294ab3e", | |
| "candidate_step": 250, | |
| "released_v61": { | |
| "objective": 0.7297131700522546, | |
| "families": { | |
| "retention": { | |
| "n": 500, | |
| "accuracy": 0.934, | |
| "nll": 0.2194680695671052, | |
| "metric": 0.934, | |
| "metric_name": "accuracy" | |
| }, | |
| "finance": { | |
| "n": 180, | |
| "accuracy": 0.7111111111111111, | |
| "nll": 0.7504884215008701, | |
| "metric": 0.7116466613734374, | |
| "metric_name": "macro-F1" | |
| }, | |
| "banking": { | |
| "n": 154, | |
| "accuracy": 0.7467532467532467, | |
| "nll": 1.2402327169109493, | |
| "metric": 0.7467532467532467, | |
| "metric_name": "accuracy" | |
| }, | |
| "sarcasm": { | |
| "n": 80, | |
| "accuracy": 0.6875, | |
| "nll": 0.6216465693736991, | |
| "metric": 0.46808510638297873, | |
| "metric_name": "positive-class F1" | |
| } | |
| } | |
| }, | |
| "selected_adapter": { | |
| "objective": 0.7384552484361269, | |
| "families": { | |
| "retention": { | |
| "n": 500, | |
| "accuracy": 0.934, | |
| "nll": 0.21906396901960715, | |
| "metric": 0.934, | |
| "metric_name": "accuracy" | |
| }, | |
| "finance": { | |
| "n": 180, | |
| "accuracy": 0.7166666666666667, | |
| "nll": 0.7359384456556678, | |
| "metric": 0.7171978179730117, | |
| "metric_name": "macro-F1" | |
| }, | |
| "banking": { | |
| "n": 154, | |
| "accuracy": 0.7467532467532467, | |
| "nll": 1.2267801923755717, | |
| "metric": 0.7467532467532467, | |
| "metric_name": "accuracy" | |
| }, | |
| "sarcasm": { | |
| "n": 80, | |
| "accuracy": 0.725, | |
| "nll": 0.6173049414476395, | |
| "metric": 0.5, | |
| "metric_name": "positive-class F1" | |
| } | |
| } | |
| }, | |
| "merged_v62": { | |
| "objective": 0.7372740069451986, | |
| "families": { | |
| "retention": { | |
| "n": 500, | |
| "accuracy": 0.934, | |
| "nll": 0.21870660245549345, | |
| "metric": 0.934, | |
| "metric_name": "accuracy" | |
| }, | |
| "finance": { | |
| "n": 180, | |
| "accuracy": 0.7111111111111111, | |
| "nll": 0.7353250763802403, | |
| "metric": 0.7121353544404619, | |
| "metric_name": "macro-F1" | |
| }, | |
| "banking": { | |
| "n": 154, | |
| "accuracy": 0.7467532467532467, | |
| "nll": 1.2266273153352905, | |
| "metric": 0.7467532467532467, | |
| "metric_name": "accuracy" | |
| }, | |
| "sarcasm": { | |
| "n": 80, | |
| "accuracy": 0.725, | |
| "nll": 0.6158682200969627, | |
| "metric": 0.5, | |
| "metric_name": "positive-class F1" | |
| } | |
| } | |
| }, | |
| "test_sha256": "d714570cac1d09849f1aea8a61ccb50a09cb9b5ac10425a7b18f0e89fd7dfc08", | |
| "limitations": [ | |
| "Exact content/group exclusions do not establish semantic or pretraining decontamination.", | |
| "Focus holdouts exclude previous local inputs; retention holdouts are reused.", | |
| "SEntFiN measures entity-level sentiment transfer, not FinEntity benchmark performance.", | |
| "Benchmarks informed target selection; final benchmark reruns are development evaluation.", | |
| "No synthetic paraphrases or benchmark test labels are used as training supervision." | |
| ], | |
| "official_decision_index": null | |
| } | |