Text Classification
MLX
Safetensors
English
Japanese
gemma4
d1a
decision-model
pull-requests
apple-silicon
quantized
on-device
experimental
8-bit precision
Instructions to use mlx-community/d1a-e2b-it-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/d1a-e2b-it-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/d1a-e2b-it-8bit --local-dir d1a-e2b-it-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download d1a_config.json from mlx-community/d1a-e2b-it-8bit: direct link, hf CLI and curl.
- Browser
- Download file 4.36 kB
-
https://huggingface.co/mlx-community/d1a-e2b-it-8bit/resolve/main/d1a_config.json
- Command line
-
hf download hf://mlx-community/d1a-e2b-it-8bit/d1a_config.json
-
curl -L -o d1a_config.json https://huggingface.co/mlx-community/d1a-e2b-it-8bit/resolve/main/d1a_config.json
4.36 kB
| { | |
| "format": "d1a-mlx", | |
| "format_version": 1, | |
| "base": "google/gemma-4-E2B-it", | |
| "base_revision": "3e22461f65e89153144f8adb70e3b8c2cc9845a7", | |
| "source": "JohnP1/d1a-e2b-it", | |
| "source_revision": "1d14f1a681a1bd3496778d89f431791af9cc71bf", | |
| "adapter_sha256": "d922cffe0a78fe6c516941b833afd4dc345120cc134c3c488f8865858280af90", | |
| "lora": 16, | |
| "head_dim": 256, | |
| "hidden_size": 1536, | |
| "temperature": 1.4142135623730947, | |
| "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", | |
| "temperature_fit": { | |
| "rows": [ | |
| "cal/rows.json", | |
| "calpr/rows.json" | |
| ], | |
| "n": 3178, | |
| "method": "min micro mean NLL over a 121-point log grid 0.25..4", | |
| "cross_validation": { | |
| "raw": { | |
| "n": 3178, | |
| "ece": 0.05269321644750151, | |
| "brier": 0.26774269342014495, | |
| "nll": 0.5260661192849185, | |
| "confident_error_rate": 0.030207677784770296, | |
| "coverage_at_5pct_error": 0.6343612334801763 | |
| }, | |
| "out_of_fold": { | |
| "n": 3178, | |
| "ece": 0.020409886004775658, | |
| "brier": 0.2628816980431792, | |
| "nll": 0.49639497637876545, | |
| "confident_error_rate": 0.01762114537444934, | |
| "coverage_at_5pct_error": 0.6261799874134676 | |
| }, | |
| "ece_ci95": { | |
| "raw": [ | |
| 0.0412701370712576, | |
| 0.06460168040334786 | |
| ], | |
| "out_of_fold": [ | |
| 0.014810248879595556, | |
| 0.03501381041208449 | |
| ], | |
| "delta": [ | |
| -0.040734042372353514, | |
| -0.01574161986134397 | |
| ] | |
| }, | |
| "separated": true, | |
| "temperatures": [ | |
| 1.4142135623730947, | |
| 1.447269237440378, | |
| 1.381912879967776, | |
| 1.447269237440378, | |
| 1.447269237440378 | |
| ], | |
| "folds": 5, | |
| "seed": 0, | |
| "samples": 1000, | |
| "groups": 1670, | |
| "unit": "source-stratified (source, group); sibling questions and variants stay together" | |
| }, | |
| "interval": { | |
| "level": 0.9, | |
| "samples": 2000, | |
| "seed": 0, | |
| "lower": 1.35034994616819, | |
| "upper": 1.4810975522865641, | |
| "questions": 3178 | |
| }, | |
| "fit_rows": [ | |
| { | |
| "rows": "cal/rows.json", | |
| "suite": "evals/v7/decision-v7", | |
| "split": "calibration", | |
| "questions": 1148 | |
| }, | |
| { | |
| "rows": "calpr/rows.json", | |
| "suite": "evals/d1a/pr-labels", | |
| "split": "development", | |
| "questions": 2030 | |
| } | |
| ], | |
| "training_suites": [ | |
| "evals/devtools-v1", | |
| "evals/documents-v1", | |
| "evals/hard-v1", | |
| "evals/v7/decision-v7" | |
| ], | |
| "training_partitions": [ | |
| "evals/d1a/ja-jglue:train", | |
| "evals/d1a/pr-labels:train", | |
| "evals/d1a/pr-labels:train-blast", | |
| "evals/d1a/pr-labels:train-ja", | |
| "evals/d1a/routing:factory-train", | |
| "evals/d1a/routing:generic-train" | |
| ], | |
| "same_corpus": [ | |
| "calpr/rows.json: SAME CORPUS: evals/d1a/pr-labels:development is an eval partition of evals/d1a/pr-labels, whose train partitions ['evals/d1a/pr-labels:train', 'evals/d1a/pr-labels:train-blast', 'evals/d1a/pr-labels:train-ja'] the checkpoint trained on" | |
| ], | |
| "in_distribution": { | |
| "allowed": true, | |
| "problems": [ | |
| "cal/rows.json: evals/v7/decision-v7 is training data of the checkpoint", | |
| "cal/rows.json: it pools 12 training source(s) ['agnews', 'amazon', 'banking77', 'boolq', 'compositional', 'dbpedia14', 'imdb', 'legacy_policy'] ...", | |
| "cal/rows.json: it reads the calibration partition of evals/v7/decision-v7, a training corpus", | |
| "calpr/rows.json: SAME CORPUS: evals/d1a/pr-labels:development is an eval partition of evals/d1a/pr-labels, whose train partitions ['evals/d1a/pr-labels:train', 'evals/d1a/pr-labels:train-blast', 'evals/d1a/pr-labels:train-ja'] the checkpoint trained on", | |
| "cannot list the sources of --data data/train-e2b-v06.jsonl (outside evals/, no sidecar train-e2b-v06.jsonl.json naming its sources), training data of d1" | |
| ] | |
| } | |
| }, | |
| "use_case_temperatures": {}, | |
| "use_case_temperature_fits": {} | |
| } | |