Instructions to use masahiroid/bert-base-ner-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use masahiroid/bert-base-ner-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download masahiroid/bert-base-ner-mlx --local-dir bert-base-ner-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -13,22 +13,29 @@ pipeline_tag: token-classification
|
|
| 13 |
|
| 14 |
# bert-base-ner-mlx
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
[dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER)(標準的なBERT-baseに
|
| 17 |
固有表現抽出ヘッドを乗せたモデル。CoNLL-2003、PER/ORG/LOC/MISCの4種)の
|
| 18 |
[MLX](https://github.com/ml-explore/mlx)版です。
|
| 19 |
|
| 20 |
-
This
|
| 21 |
-
[dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER).
|
| 22 |
-
All credit for the original model goes to its author.
|
| 23 |
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
`mlx-embeddings`はembedding/reranker用のpooling出力をターゲットにしており、トークン単位の
|
| 27 |
分類ヘッド(各トークンに対して独立にラベルを出す構成)には対応していないため、**MLXでの
|
| 28 |
実装をゼロから書き起こして**変換しています。同梱の`bert_ner_mlx.py`が必要です。構造自体は
|
| 29 |
標準的なpost-norm BERTエンコーダー + 線形分類ヘッドとシンプルです。
|
| 30 |
|
| 31 |
-
## 使い方
|
| 32 |
|
| 33 |
```python
|
| 34 |
import mlx.core as mx
|
|
@@ -55,17 +62,28 @@ for tok, label_id in zip(tokens, labels):
|
|
| 55 |
print(tok, model.config.id2label[label_id] if hasattr(model, "config") else label_id)
|
| 56 |
```
|
| 57 |
|
|
|
|
|
|
|
|
|
|
| 58 |
ラベルは元モデルと同じ: `{0: "O", 1: "B-MISC", 2: "I-MISC", 3: "B-PER", 4: "I-PER",
|
| 59 |
5: "B-ORG", 6: "I-ORG", 7: "B-LOC", 8: "I-LOC"}`。
|
| 60 |
|
| 61 |
-
## 精度検証
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
PyTorch fp32リファレンスと、実際の文章1件(人名・地名・組織名を含む)で比較:
|
| 64 |
|
| 65 |
-
| 精度 |
|
| 66 |
|---|---|---|
|
| 67 |
| MLX fp32 | 1.0 | 100% |
|
| 68 |
-
| MLX fp16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
fp16変換の際、attention maskのマスク値に`-1e9`のようなfp16で表現できない大きな負数を使うと、
|
| 71 |
マスクされていない(`mask=1`)位置で`0 * (-inf)`が発生してNaNになる罠があった。
|
|
@@ -76,13 +94,13 @@ fp16の範囲内に収まる`-1e4`に変更して解消している(詳細は`
|
|
| 76 |
|
| 77 |
| Item | Value |
|
| 78 |
|---|---|
|
| 79 |
-
| Base model | `dslim/bert-base-NER`
|
| 80 |
| Precision | float16 |
|
| 81 |
-
| Framework | MLX
|
| 82 |
|
| 83 |
## Notes
|
| 84 |
|
| 85 |
- This is a community conversion, not an official release from the original author.
|
| 86 |
- 本変換は非公式のコミュニティ版です。
|
| 87 |
-
-
|
| 88 |
-
|
|
|
|
| 13 |
|
| 14 |
# bert-base-ner-mlx
|
| 15 |
|
| 16 |
+
This is an unofficial [MLX](https://github.com/ml-explore/mlx) conversion of
|
| 17 |
+
[dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) (a standard
|
| 18 |
+
BERT-base with a named-entity-recognition head on top, trained on CoNLL-2003:
|
| 19 |
+
PER/ORG/LOC/MISC). All credit for the original model goes to its author.
|
| 20 |
+
|
| 21 |
[dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER)(標準的なBERT-baseに
|
| 22 |
固有表現抽出ヘッドを乗せたモデル。CoNLL-2003、PER/ORG/LOC/MISCの4種)の
|
| 23 |
[MLX](https://github.com/ml-explore/mlx)版です。
|
| 24 |
|
| 25 |
+
## This cannot be loaded with mlx-embeddings / mlx-embeddingsでは読み込めません
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
`mlx-embeddings` targets pooled embedding/reranker outputs and doesn't
|
| 28 |
+
support a per-token classification head. This model was **reimplemented from
|
| 29 |
+
scratch for MLX** and requires the bundled `bert_ner_mlx.py`. The
|
| 30 |
+
architecture itself is simple: a standard post-norm BERT encoder plus a
|
| 31 |
+
linear classification head.
|
| 32 |
|
| 33 |
`mlx-embeddings`はembedding/reranker用のpooling出力をターゲットにしており、トークン単位の
|
| 34 |
分類ヘッド(各トークンに対して独立にラベルを出す構成)には対応していないため、**MLXでの
|
| 35 |
実装をゼロから書き起こして**変換しています。同梱の`bert_ner_mlx.py`が必要です。構造自体は
|
| 36 |
標準的なpost-norm BERTエンコーダー + 線形分類ヘッドとシンプルです。
|
| 37 |
|
| 38 |
+
## Usage / 使い方
|
| 39 |
|
| 40 |
```python
|
| 41 |
import mlx.core as mx
|
|
|
|
| 62 |
print(tok, model.config.id2label[label_id] if hasattr(model, "config") else label_id)
|
| 63 |
```
|
| 64 |
|
| 65 |
+
Labels are the same as the original model: `{0: "O", 1: "B-MISC", 2: "I-MISC",
|
| 66 |
+
3: "B-PER", 4: "I-PER", 5: "B-ORG", 6: "I-ORG", 7: "B-LOC", 8: "I-LOC"}`.
|
| 67 |
+
|
| 68 |
ラベルは元モデルと同じ: `{0: "O", 1: "B-MISC", 2: "I-MISC", 3: "B-PER", 4: "I-PER",
|
| 69 |
5: "B-ORG", 6: "I-ORG", 7: "B-LOC", 8: "I-LOC"}`。
|
| 70 |
|
| 71 |
+
## Accuracy / 精度検証
|
| 72 |
+
|
| 73 |
+
Compared against the PyTorch fp32 reference on a real sentence containing
|
| 74 |
+
person/location/organization entities:
|
| 75 |
|
| 76 |
PyTorch fp32リファレンスと、実際の文章1件(人名・地名・組織名を含む)で比較:
|
| 77 |
|
| 78 |
+
| Precision / 精度 | Logits cosine sim. | Label agreement |
|
| 79 |
|---|---|---|
|
| 80 |
| MLX fp32 | 1.0 | 100% |
|
| 81 |
+
| MLX fp16 (this release) | 0.99999994 | 100% |
|
| 82 |
+
|
| 83 |
+
During fp16 conversion, using an attention-mask value like `-1e9` (which
|
| 84 |
+
doesn't fit in fp16) caused `0 * (-inf) = NaN` at unmasked (`mask=1`)
|
| 85 |
+
positions. Fixed by switching to `-1e4`, which fits fp16's range (full
|
| 86 |
+
details are in the conversion-toolkit repo, not `SECURITY.md`).
|
| 87 |
|
| 88 |
fp16変換の際、attention maskのマスク値に`-1e9`のようなfp16で表現できない大きな負数を使うと、
|
| 89 |
マスクされていない(`mask=1`)位置で`0 * (-inf)`が発生してNaNになる罠があった。
|
|
|
|
| 94 |
|
| 95 |
| Item | Value |
|
| 96 |
|---|---|
|
| 97 |
+
| Base model | `dslim/bert-base-NER` (BERT-base, 108M params) |
|
| 98 |
| Precision | float16 |
|
| 99 |
+
| Framework | MLX (from-scratch `bert_ner_mlx.py`) |
|
| 100 |
|
| 101 |
## Notes
|
| 102 |
|
| 103 |
- This is a community conversion, not an official release from the original author.
|
| 104 |
- 本変換は非公式のコミュニティ版です。
|
| 105 |
+
- Security audit uses [model-audit-lite](https://github.com/masahirocom/model-audit-lite)
|
| 106 |
+
(see `SECURITY.md` for details).
|