Text Classification
MLX
Safetensors
English
Japanese
gemma4
d1a
decision-model
structured-output
classification
apple-silicon
quantized
pull-requests
8-bit precision
Instructions to use mlx-community/d1a-e4b-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/d1a-e4b-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/d1a-e4b-8bit --local-dir d1a-e4b-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download d1a_config.json from mlx-community/d1a-e4b-8bit: direct link, hf CLI and curl.
- Browser
- Download file 3.1 kB
-
https://huggingface.co/mlx-community/d1a-e4b-8bit/resolve/main/d1a_config.json
- Command line
-
hf download hf://mlx-community/d1a-e4b-8bit/d1a_config.json
-
curl -L -o d1a_config.json https://huggingface.co/mlx-community/d1a-e4b-8bit/resolve/main/d1a_config.json
3.1 kB
| { | |
| "format": "d1a-mlx", | |
| "format_version": 1, | |
| "base": "google/gemma-4-E4B", | |
| "base_revision": "411aa17b749aa952df1359d2dcea73917a544d9a", | |
| "source": "JohnP1/d1a-e4b", | |
| "source_revision": "3ca01b824280cacf027826b0ded8632f242a7e8b", | |
| "adapter_sha256": "739ce962c3ae630243ee53b212a822e8b2feee41080b68d5b460fd0ebb19e4ea", | |
| "lora": 16, | |
| "head_dim": 256, | |
| "hidden_size": 2560, | |
| "temperature": 1.9543199368684914, | |
| "leading_ids": [ | |
| 2 | |
| ], | |
| "bos_id": 2, | |
| "delimiter_ids": [ | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10 | |
| ], | |
| "pad_id": 0, | |
| "dtype": "bfloat16", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine", | |
| "language_model.model.embed_tokens_per_layer": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "embeddings": true | |
| }, | |
| "head": "head.safetensors", | |
| "use_case_temperatures": { | |
| "routing": 1.1755479062836087 | |
| }, | |
| "use_case_temperature_fits": { | |
| "routing": { | |
| "rows": [ | |
| "phase-d3/gate/suites/routing_generic-development/head/rows.json", | |
| "phase-d3/gate/suites/routing_handlabelled-45/head/rows.json" | |
| ], | |
| "n": 315, | |
| "method": "min micro mean NLL over a 121-point log grid 0.25..4", | |
| "cross_validation": { | |
| "raw": { | |
| "n": 315, | |
| "ece": 0.005376748980220513, | |
| "brier": 0.02213792789102334, | |
| "nll": 0.037784826756766074, | |
| "confident_error_rate": 0.0031746031746031746, | |
| "coverage_at_5pct_error": 1.0 | |
| }, | |
| "out_of_fold": { | |
| "n": 315, | |
| "ece": 0.008392239537266366, | |
| "brier": 0.021994761576082954, | |
| "nll": 0.0385561510340784, | |
| "confident_error_rate": 0.0031746031746031746, | |
| "coverage_at_5pct_error": 1.0 | |
| }, | |
| "ece_ci95": { | |
| "raw": [ | |
| 0.003303220868466807, | |
| 0.018871250910842064 | |
| ], | |
| "out_of_fold": [ | |
| 0.0058853472476678124, | |
| 0.022409565392811873 | |
| ], | |
| "delta": [ | |
| -0.001788803325547818, | |
| 0.007955193851064562 | |
| ] | |
| }, | |
| "separated": false, | |
| "temperatures": [ | |
| 1.2311444133449163, | |
| 1.148698354997035, | |
| 1.2893703084395791, | |
| 1.2311444133449163, | |
| 1.0233738919967748 | |
| ], | |
| "folds": 5, | |
| "seed": 0, | |
| "samples": 1000, | |
| "groups": 315, | |
| "unit": "source-stratified (source, group); sibling questions and variants stay together" | |
| }, | |
| "interval": { | |
| "level": 0.9, | |
| "samples": 2000, | |
| "seed": 0, | |
| "lower": 0.6744039221992122, | |
| "upper": 1.5157165665103978, | |
| "questions": 315 | |
| }, | |
| "fit_rows": [ | |
| { | |
| "rows": "phase-d3/gate/suites/routing_generic-development/head/rows.json", | |
| "suite": "evals/d1a/routing", | |
| "split": "generic-development", | |
| "questions": 270 | |
| }, | |
| { | |
| "rows": "phase-d3/gate/suites/routing_handlabelled-45/head/rows.json", | |
| "suite": "evals/d1a/routing", | |
| "split": "handlabelled-45", | |
| "questions": 45 | |
| } | |
| ], | |
| "training_suites": [ | |
| "evals/v7/decision-v7" | |
| ], | |
| "training_partitions": [], | |
| "in_distribution": { | |
| "allowed": true, | |
| "problems": [ | |
| "cannot list the sources of --data train.jsonl (outside evals/, no sidecar train.jsonl.json naming its sources), training data of routing-temp-v061/stub/d1a-e4b" | |
| ] | |
| } | |
| } | |
| } | |
| } | |