Update model card: added convergentintel tag, added DISC section
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ tags:
|
|
| 14 |
- generated_from_trainer
|
| 15 |
- finetune
|
| 16 |
- symbioticai
|
|
|
|
| 17 |
language:
|
| 18 |
- en
|
| 19 |
license: apache-2.0
|
|
@@ -125,6 +126,20 @@ Limitations and Bias
|
|
| 125 |
* Inherited Bias: This model inherits any biases present in the base model (SmolLM2-CoT-360M) and the training datasets.
|
| 126 |
### Acknowledgements
|
| 127 |
You're doing great!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
## Citations
|
| 129 |
If you use TRL in your work, please cite the library:
|
| 130 |
@misc{vonwerra2022trl,
|
|
|
|
| 14 |
- generated_from_trainer
|
| 15 |
- finetune
|
| 16 |
- symbioticai
|
| 17 |
+
- convergentintel
|
| 18 |
language:
|
| 19 |
- en
|
| 20 |
license: apache-2.0
|
|
|
|
| 126 |
* Inherited Bias: This model inherits any biases present in the base model (SmolLM2-CoT-360M) and the training datasets.
|
| 127 |
### Acknowledgements
|
| 128 |
You're doing great!
|
| 129 |
+
## Discrepancy Calculus Foundation
|
| 130 |
+
|
| 131 |
+
This model is part of the [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow) portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model *should* produce and what it *actually* produces.
|
| 132 |
+
|
| 133 |
+
DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as **structural signals** that reveal the geometry of the learning problem. Key concepts:
|
| 134 |
+
|
| 135 |
+
- **Discrepancy Operator (D):** Measures the gap between expected and observed behavior at each training step
|
| 136 |
+
- **Jump Sets:** Boundaries where model behavior changes discontinuously — these are *features*, not bugs
|
| 137 |
+
- **Ghost Imprinting:** Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal
|
| 138 |
+
|
| 139 |
+
For the full mathematical treatment, see [Discrepancy Calculus: Foundations and Core Theory](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194).
|
| 140 |
+
|
| 141 |
+
**Citation chain:** [Structure Over Scale](https://huggingface.co/reaperdoesntknow/Structure-Over-Scale) (DOI: 10.57967/hf/8165) → [Three Teachers to Dual Cognition](https://huggingface.co/reaperdoesntknow/DualMind_Methodolgy) (DOI: 10.57967/hf/8184) → [Discrepancy Calculus](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194)
|
| 142 |
+
|
| 143 |
## Citations
|
| 144 |
If you use TRL in your work, please cite the library:
|
| 145 |
@misc{vonwerra2022trl,
|