Text Classification
MLX
Safetensors
jev-style
decision-model
system-one
calibration
long-context
multilingual
qwen3.5
on-device
Instructions to use chaoliangUNSW/Jev-Style-0.8B-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-0.8B-Decision-v3-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Jev-Style-0.8B-Decision-v3-MLX chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX
- jev-style
How to use chaoliangUNSW/Jev-Style-0.8B-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-0.8B-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 8bit/config.json from chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX: direct link, hf CLI and curl.
- Browser
- Download file 2.2 kB
-
https://huggingface.co/chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX/resolve/main/8bit/config.json
- Command line
-
hf download hf://chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX/8bit/config.json
-
curl -L -o config.json https://huggingface.co/chaoliangUNSW/Jev-Style-0.8B-Decision-v3-MLX/resolve/main/8bit/config.json
2.2 kB
| { | |
| "architectures": [ | |
| "Qwen3_5ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3584, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.17.0", | |
| "use_cache": true, | |
| "vocab_size": 248320 | |
| } |