Text Classification
Transformers
Safetensors
qwen3_5
image-text-to-text
decision-model
typed-decisions
classification
routing
calibrated-probabilities
Instructions to use ironbcc/Seb-9B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ironbcc/Seb-9B-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ironbcc/Seb-9B-v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ironbcc/Seb-9B-v2") model = AutoModelForMultimodalLM.from_pretrained("ironbcc/Seb-9B-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
add blog/post.md
Browse files- blog/post.md +3 -3
blog/post.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
# Seb-9B-v2: beats hosted Jev 1.13 on the Decision Index, at 22 ms, on your own hardware
|
| 2 |
|
| 3 |
-
Seb-9B-v2 scores **59.16** on the Decision Index
|
| 4 |
|
| 5 |
-
|
| 6 |
|
| 7 |

|
| 8 |
|
| 9 |
## TL;DR
|
| 10 |
|
| 11 |
-
- **Quality.** 0.801 mean accuracy over 17 public suites (our v1 0.793, hosted Jev 1.13 0.786). BANKING77 0.973, jailbreak detection 0.940, model routing 0.980. On 420 public decision rows it
|
| 12 |
- **Speed.** About 22 ms per decision on one RTX PRO 6000 and about 88 ms on an Apple M5 Max, up to roughly 87 decisions a second per GPU.
|
| 13 |
- **Decision Index.** 59.16 on the 0.3 public index, against 57.96 for hosted Jev 1.13 and 60.70 for Jev 1.14. Ahead of Jev 1.13 on 22 of 37 benchmarks and in 4 of 5 areas.
|
| 14 |
|
|
|
|
| 1 |
# Seb-9B-v2: beats hosted Jev 1.13 on the Decision Index, at 22 ms, on your own hardware
|
| 2 |
|
| 3 |
+
Seb-9B-v2 is a 9B decision model that scores **59.16** on the Decision Index, ahead of hosted Jev 1.13 (57.96). It runs in about **22 ms** a decision on one GPU or **88 ms** on a Mac, and your data never leaves your machine. On public decision rows it edges out Claude Haiku and gpt-6-luna (0.798 vs 0.795 and 0.779, within noise). Put in front of Claude Opus as a first tier, it answered about half the requests itself and kept Opus-level accuracy overall, at an estimated **51% lower cost**.
|
| 4 |
|
| 5 |
+
You give it a situation, a question and a few options, and it returns a probability for every option in one forward pass. No text is generated, so there is nothing to parse. It reads images, takes inputs up to 32k tokens, and speaks both a regular chat API and the System One API.
|
| 6 |
|
| 7 |

|
| 8 |
|
| 9 |
## TL;DR
|
| 10 |
|
| 11 |
+
- **Quality.** 0.801 mean accuracy over 17 public suites (our v1 0.793, hosted Jev 1.13 0.786). BANKING77 0.973, jailbreak detection 0.940, model routing 0.980. On 420 public decision rows it edges out gpt-6-luna and Claude Haiku (medium effort), within noise, and trails Claude Opus.
|
| 12 |
- **Speed.** About 22 ms per decision on one RTX PRO 6000 and about 88 ms on an Apple M5 Max, up to roughly 87 decisions a second per GPU.
|
| 13 |
- **Decision Index.** 59.16 on the 0.3 public index, against 57.96 for hosted Jev 1.13 and 60.70 for Jev 1.14. Ahead of Jev 1.13 on 22 of 37 benchmarks and in 4 of 5 areas.
|
| 14 |
|