Text Generation
MLX
Safetensors
jev-style
English
qwen3_5
decision-model
classification
calibration
qwen3.5
single-prefill
conversational
Instructions to use chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - jev-style
How to use chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16 with jev-style:
# Apple silicon pip install "jev-style[mlx]"
from jev_style import JevStyle, noul, choice js = JevStyle.from_pretrained("chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16") out = js.decide("I was charged twice for one order.", { "billing": noul("This message is about billing."), "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]), }) print(out["answers"]["team"]["choice"]) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Download SHA256SUMS.json from chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16: direct link, hf CLI and curl.
- Browser
- Download file 3.67 kB
-
https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16/resolve/main/SHA256SUMS.json
- Command line
-
hf download hf://chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16/SHA256SUMS.json
-
curl -L -o SHA256SUMS.json https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16/resolve/main/SHA256SUMS.json
3.67 kB
| { | |
| "LICENSE": { | |
| "bytes": 11343, | |
| "sha256": "50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32" | |
| }, | |
| "README.md": { | |
| "bytes": 11002, | |
| "sha256": "5a95dc52b63e1b6c38161e41763c2cbf131063c9445d755a67c753bc8190b90b" | |
| }, | |
| "calibration.json": { | |
| "bytes": 362, | |
| "sha256": "d9dbb2354233214fc7ae31937583b6959ac97f15755d72027e3589770e439c1d" | |
| }, | |
| "chat_template.jinja": { | |
| "bytes": 29, | |
| "sha256": "c89ccc96b9280cec1ce79c1985cb0e18efe9c839d9434e0971a87cc7907553dc" | |
| }, | |
| "config.json": { | |
| "bytes": 1908, | |
| "sha256": "1f6a6a0f0d049daeb9db5967d9a779bd57349bd534b0492b4fa324a3c97794e6" | |
| }, | |
| "decision_config.json": { | |
| "bytes": 499, | |
| "sha256": "582aff7f97724134ec990b0ec2e46c169b180ac5ede3db1a2f9c3f531802fe33" | |
| }, | |
| "evaluation/baseline_sensitivity.json": { | |
| "bytes": 2015, | |
| "sha256": "aadc4566710a397044edbfb9c353ee2e0baf14a6deb5e30f4234eabd66294026" | |
| }, | |
| "evaluation/data_manifest.json": { | |
| "bytes": 10680, | |
| "sha256": "8d03d4bba9400ffe062b248733213a6e67a3d6c187340e9aa796c319f2feef23" | |
| }, | |
| "evaluation/deployment.json": { | |
| "bytes": 501, | |
| "sha256": "513d6fd255784a467b5344e8186067198897592acf692d6c3d3bb7798c572e65" | |
| }, | |
| "evaluation/laya_source.json": { | |
| "bytes": 97, | |
| "sha256": "b12ecce8dca6afad9e43c31c2385be255514d78856009ef9a6222bc955ca0757" | |
| }, | |
| "evaluation/laya_typed_source.json": { | |
| "bytes": 113, | |
| "sha256": "c2c2bc4931bb489636c5471f25f2fa31c3baca347c0465f119b8039aac1d3619" | |
| }, | |
| "evaluation/packaging_verification.json": { | |
| "bytes": 338, | |
| "sha256": "2396b1f51b00d4f8fe6f7c50dcf1d479899cc6d9ff12392894a9fa75e6d01570" | |
| }, | |
| "evaluation/reference_comparison.json": { | |
| "bytes": 27042, | |
| "sha256": "36f56a490fc67e774cbb25b38d4dc9b5e3a42e1f65fcd748af092e127a98eff8" | |
| }, | |
| "generation_config.json": { | |
| "bytes": 117, | |
| "sha256": "781b10c2d2c264c99a5d3e1458d403fb5d8baf2ecfadbcfd92d107fe049261fb" | |
| }, | |
| "jev_mlx_client.py": { | |
| "bytes": 5397, | |
| "sha256": "15038fc9d57e4acbea6de5a478a59f96e387710336f6d5837ba603bd4c55b93b" | |
| }, | |
| "model.safetensors": { | |
| "bytes": 3763898548, | |
| "sha256": "71c6a2f6e1a5d4c3e4465fdfe452989485f86e2bf9fddad61e03706e6a5fe871" | |
| }, | |
| "model.safetensors.index.json": { | |
| "bytes": 28024, | |
| "sha256": "3f8d2a42c038ae4ba50c9439964731e4e78a438876a0e6515ad2a12c8bca1524" | |
| }, | |
| "requirements.txt": { | |
| "bytes": 48, | |
| "sha256": "bd0ea5e5ec70be46d50f4b4bdc2576ddefc2f5e613c234fdc706b764029c9f3b" | |
| }, | |
| "tokenizer.json": { | |
| "bytes": 19989325, | |
| "sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523" | |
| }, | |
| "tokenizer_config.json": { | |
| "bytes": 1156, | |
| "sha256": "303f948bfd44621a24f1d90b6330d8280076d08b60152f5851d9e9921c0b570e" | |
| }, | |
| "evaluation/chart_data.json": { | |
| "bytes": 4588, | |
| "sha256": "0db9855803eb514792a906ff04b1d9ccdcba81babeedcffdd9ae34131f8b04f1" | |
| }, | |
| "figures/calibration.svg": { | |
| "bytes": 28967, | |
| "sha256": "8433aa3a878362e977defe21ccc4400d63c3eba07afa7725535c6fa7fb93d0fc" | |
| }, | |
| "figures/robustness.png": { | |
| "bytes": 125258, | |
| "sha256": "41c317f25853b88452c8515cddf8773fbcbd3d354ec718d90ab6bc01716bd4a0" | |
| }, | |
| "figures/benchmark.png": { | |
| "bytes": 188910, | |
| "sha256": "5a3a782cf203a586a8ffa7bef3006a79906ad4553b8548af4b62a63f6723a6dc" | |
| }, | |
| "figures/benchmark.svg": { | |
| "bytes": 22570, | |
| "sha256": "187ee46cfdccc078fa5725e9668b28dad2456b9920d6e1bc26f6ec133a9d5e0a" | |
| }, | |
| "figures/robustness.svg": { | |
| "bytes": 11821, | |
| "sha256": "1f54a0e66a5bcceafad85595f91db1a0ed5f0eb6b4c45b726bafd8a941f53600" | |
| }, | |
| "figures/calibration.png": { | |
| "bytes": 183790, | |
| "sha256": "2a4e163354b0d0d31bf5fcdfcfbcf726fb152fb2f6419432ddddaec3b475a921" | |
| } | |
| } | |