Text Classification
Transformers
Safetensors
English
mistral3
image-text-to-text
decision-model
typed-decisions
schema-head
jev
calibration
decode-free
Instructions to use StandardThinking/StandardOne-3B-SH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StandardThinking/StandardOne-3B-SH with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="StandardThinking/StandardOne-3B-SH")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("StandardThinking/StandardOne-3B-SH") model = AutoModelForMultimodalLM.from_pretrained("StandardThinking/StandardOne-3B-SH", device_map="auto") - Notebooks
- Google Colab
- Kaggle
v3 card: benchmark charts from the Decision Index guide
Browse files- .gitattributes +8 -0
- README.md +21 -0
- SHA256SUMS +9 -1
- assets/charts/01-index-vs-size.png +3 -0
- assets/charts/02-retrieval-classification.png +3 -0
- assets/charts/03-tools-automation.png +3 -0
- assets/charts/04-product-search.png +3 -0
- assets/charts/05-claim-verification.png +3 -0
- assets/charts/06-home-appliance.png +3 -0
- assets/charts/07-contract-nli.png +3 -0
- assets/charts/08-chords.png +3 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tekken.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tekken.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/charts/01-index-vs-size.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/charts/02-retrieval-classification.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/charts/03-tools-automation.png filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
assets/charts/04-product-search.png filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
assets/charts/05-claim-verification.png filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
assets/charts/06-home-appliance.png filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
assets/charts/07-contract-nli.png filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
assets/charts/08-chords.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -65,6 +65,27 @@ and [standardone-3b-sh-v3](https://huggingface.co/datasets/StandardThinking/Stan
|
|
| 65 |
generator was part of training (HoVer among them); evaluated items never were. The other rows are accuracy in percent
|
| 66 |
on identical items: the v2 column with the reference server in `code/`, the v3 column with the Standard One engine.
|
| 67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
## Changes in v3
|
| 69 |
|
| 70 |
- **Further training on synthetic decision data.** v3 continues from v2 on decision items built for this round, mostly our own
|
|
|
|
| 65 |
generator was part of training (HoVer among them); evaluated items never were. The other rows are accuracy in percent
|
| 66 |
on identical items: the v2 column with the reference server in `code/`, the v3 column with the Standard One engine.
|
| 67 |
|
| 68 |
+
## Benchmark charts
|
| 69 |
+
|
| 70 |
+
Decision Index 0.3 public index, board data of 2026-10-12; Standard One self-scored with the official kit (see the footnote of each chart).
|
| 71 |
+
The same charts with notes: [Standard One SH on the Decision Index](https://standardthinking.ai/resources/guides/standard-one-sh-decision-index/).
|
| 72 |
+
|
| 73 |
+

|
| 74 |
+
|
| 75 |
+

|
| 76 |
+
|
| 77 |
+

|
| 78 |
+
|
| 79 |
+

|
| 80 |
+
|
| 81 |
+

|
| 82 |
+
|
| 83 |
+

|
| 84 |
+
|
| 85 |
+

|
| 86 |
+
|
| 87 |
+

|
| 88 |
+
|
| 89 |
## Changes in v3
|
| 90 |
|
| 91 |
- **Further training on synthetic decision data.** v3 continues from v2 on decision items built for this round, mostly our own
|
SHA256SUMS
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747 LICENSE
|
| 2 |
-
|
| 3 |
331b249682cd52226c50e533f59825184997f3b31f9a62b2c3fea940db6999c5 SYSTEM_PROMPT.txt
|
| 4 |
e62f05da25555a4c109d0f413eb673d328fcc40f7c82537c61631611f6954372 chat_template.jinja
|
| 5 |
3208d5b86b4ce169d39302f52944f8898e42c6917aab121524bd54cae5af9cb0 config.json
|
|
@@ -22,3 +22,11 @@ f59f7294e4f26383d0ea93840fe21cf197784be0842a8301a0343e8c34ed0d6d tokenizer_conf
|
|
| 22 |
1b31b60dc0273ef671e230b3b1db79efd2a7de1410feef380757fc4cb2a316d9 code/serve_head.py
|
| 23 |
86ab2a272b51d18fe7fffe78aab58bdf917d3b8ccf32b064efceeb5e19786aa7 head/schema_head.safetensors
|
| 24 |
0dc3867d770916b77ebb7adfeab1aa0708a2b58a9428f390c84a2d0a71ff044e head/schema_head_config.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
1495e1e757ef4d0925a2350563cf5754bb23c51701a8ec4fb3c5cdcbedae6747 LICENSE
|
| 2 |
+
5b118d43ab6d82e9b6e3afd0837879b47a7e1f847195c5258a279651f61d5005 README.md
|
| 3 |
331b249682cd52226c50e533f59825184997f3b31f9a62b2c3fea940db6999c5 SYSTEM_PROMPT.txt
|
| 4 |
e62f05da25555a4c109d0f413eb673d328fcc40f7c82537c61631611f6954372 chat_template.jinja
|
| 5 |
3208d5b86b4ce169d39302f52944f8898e42c6917aab121524bd54cae5af9cb0 config.json
|
|
|
|
| 22 |
1b31b60dc0273ef671e230b3b1db79efd2a7de1410feef380757fc4cb2a316d9 code/serve_head.py
|
| 23 |
86ab2a272b51d18fe7fffe78aab58bdf917d3b8ccf32b064efceeb5e19786aa7 head/schema_head.safetensors
|
| 24 |
0dc3867d770916b77ebb7adfeab1aa0708a2b58a9428f390c84a2d0a71ff044e head/schema_head_config.json
|
| 25 |
+
95a7b9bd0d618297650ab75632c7bf1f3d4ec1739119690d7c248bf3e9a00528 assets/charts/01-index-vs-size.png
|
| 26 |
+
9b27154612b81237d02ac0384412cb1a41f9955e2b4db437f9aa25eb53b59f63 assets/charts/02-retrieval-classification.png
|
| 27 |
+
a193f8032ef5d65c2783ecb6f0b43270b01abe95e4582b69dadfc285736888bd assets/charts/03-tools-automation.png
|
| 28 |
+
7f008ebd14e6d3074fb72a06f3a76f17734225bf02f897bb5b356dd0c1963e02 assets/charts/04-product-search.png
|
| 29 |
+
a484d13ea51d3bd5a3501e808cf5447bf9cfefb2800cffd8410276dbbe3a1b2d assets/charts/05-claim-verification.png
|
| 30 |
+
10df32eb145fcd14176611c6229f034440d93683848ca28672677caa953936fa assets/charts/06-home-appliance.png
|
| 31 |
+
7f1c72e812c9652552bfcbc78210327b188435157296017b8b31cfc124432373 assets/charts/07-contract-nli.png
|
| 32 |
+
47e9510297624fa13d5bba0deafd2f37441f33b23019d5364357af83274a5d5e assets/charts/08-chords.png
|
assets/charts/01-index-vs-size.png
ADDED
|
Git LFS Details
|
assets/charts/02-retrieval-classification.png
ADDED
|
Git LFS Details
|
assets/charts/03-tools-automation.png
ADDED
|
Git LFS Details
|
assets/charts/04-product-search.png
ADDED
|
Git LFS Details
|
assets/charts/05-claim-verification.png
ADDED
|
Git LFS Details
|
assets/charts/06-home-appliance.png
ADDED
|
Git LFS Details
|
assets/charts/07-contract-nli.png
ADDED
|
Git LFS Details
|
assets/charts/08-chords.png
ADDED
|
Git LFS Details
|