Text Classification
Transformers
Safetensors
Laya
English
oscar-1
decision-model
system-one
calibrated-decisions
rlcd
ettin
classification
routing
scoring
guardrails
moderation
reinforcement-learning
commercial-use
Eval Results (legacy)
Instructions to use mgoeckel/oscar-1-400m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mgoeckel/oscar-1-400m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mgoeckel/oscar-1-400m")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mgoeckel/oscar-1-400m", device_map="auto") - Laya
How to use mgoeckel/oscar-1-400m with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
oscar-1: paired-read CIs regenerated under the case-clustered unit (method fix); verdict wording matches sign of CI
Browse files
README.md
CHANGED
|
@@ -104,9 +104,9 @@ include one invalid entry (`choice:11+`, clamped at load) — accuracy is unaffe
|
|
| 104 |
|
| 105 |
## Paired reads
|
| 106 |
|
| 107 |
-
Paired with the previous generation: sealed overall +21.4 pp [+
|
| 108 |
|
| 109 |
-
Paired with `oscar-1-150m`: sealed overall +2.3 pp [
|
| 110 |
|
| 111 |
## Calibration (raw vs served)
|
| 112 |
|
|
|
|
| 104 |
|
| 105 |
## Paired reads
|
| 106 |
|
| 107 |
+
Paired with the previous generation: sealed overall +21.4 pp [+18.0, +24.6]; 119 decisions right only in the previous generation, 384 only in this checkpoint (exact McNemar p ≈ 0). The delta is clear.
|
| 108 |
|
| 109 |
+
Paired with `oscar-1-150m`: sealed overall +2.3 pp [+0.4, +4.3]; 61 decisions right only in `oscar-1-150m`, 90 only in this checkpoint (exact McNemar p = 0.0224). The delta is clear.
|
| 110 |
|
| 111 |
## Calibration (raw vs served)
|
| 112 |
|