Text Classification
MLX
Safetensors
jev-style
qwen3_5
decision-model
decision-making
system-one
calibration
long-context
qwen3.5
apple-silicon
on-device
llm-routing
guardrails
Instructions to use chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX --local-dir Jev-Style-2B-Decision-v3-MLX
- jev-style
How to use chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX with jev-style:
# Apple silicon pip install "jev-style[mlx]"
from jev_style import JevStyle, noul, choice js = JevStyle.from_pretrained("chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX") 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
- Atomic Chat
Download validation/parity/cross_format_dp.json from chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX: direct link, hf CLI and curl.
- Browser
- Download file 1.55 kB
-
https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX/resolve/11ce5d718e22412b38624bb863a1eee73c0a5934/validation/parity/cross_format_dp.json
- Command line
-
hf download hf://chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX@11ce5d718e22412b38624bb863a1eee73c0a5934/validation/parity/cross_format_dp.json
-
curl -L -o cross_format_dp.json https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX/resolve/11ce5d718e22412b38624bb863a1eee73c0a5934/validation/parity/cross_format_dp.json
1.55 kB
| { | |
| "base:torch_fp32_cpu": { | |
| "n": 43, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 4.782633115096857e-06, | |
| "mean_max_abs_dp": 6.972375795818997e-07 | |
| }, | |
| "base:gguf_f16": { | |
| "n": 43, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 0.0006297677378335198, | |
| "mean_max_abs_dp": 0.00017737997866918594 | |
| }, | |
| "base:gguf_q8_0": { | |
| "n": 43, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 0.021289327356281362, | |
| "mean_max_abs_dp": 0.0044768677260933745 | |
| }, | |
| "base:gguf_q4_k_m": { | |
| "n": 43, | |
| "top1_agree": 0.9767441860465116, | |
| "max_abs_dp": 0.15778925110927658, | |
| "mean_max_abs_dp": 0.047022506153486646 | |
| }, | |
| "base:mlx_bf16": { | |
| "n": 43, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 0.010765431767972844, | |
| "mean_max_abs_dp": 0.003890125022245109 | |
| }, | |
| "base:mlx_8bit": { | |
| "n": 43, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 0.04628699142360499, | |
| "mean_max_abs_dp": 0.007026009064181663 | |
| }, | |
| "gate:gguf_f16": { | |
| "n": 1000, | |
| "top1_agree": 1.0, | |
| "max_abs_dp": 0.0013728371250730786, | |
| "mean_max_abs_dp": 0.00012138780447113503 | |
| }, | |
| "gate:gguf_q8_0": { | |
| "n": 1000, | |
| "top1_agree": 0.997, | |
| "max_abs_dp": 0.033479594816581415, | |
| "mean_max_abs_dp": 0.0020247272188215755 | |
| }, | |
| "gate:gguf_q4_k_m": { | |
| "n": 1000, | |
| "top1_agree": 0.957, | |
| "max_abs_dp": 0.34599917206983777, | |
| "mean_max_abs_dp": 0.02317308476687987 | |
| }, | |
| "gate:mlx_bf16": { | |
| "n": 1000, | |
| "top1_agree": 0.997, | |
| "max_abs_dp": 0.03549758339084519, | |
| "mean_max_abs_dp": 0.0025865935031305484 | |
| }, | |
| "gate:mlx_8bit": { | |
| "n": 1000, | |
| "top1_agree": 0.996, | |
| "max_abs_dp": 0.1623697296878569, | |
| "mean_max_abs_dp": 0.0039011049015487734 | |
| } | |
| } |