Update README.md
Browse files
README.md
CHANGED
|
@@ -9,32 +9,28 @@ metrics:
|
|
| 9 |
model-index:
|
| 10 |
- name: ModernBERT-large-llm-router
|
| 11 |
results: []
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
-
|
| 17 |
# ModernBERT-large-llm-router
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on
|
| 20 |
-
|
|
|
|
| 21 |
- Loss: 0.0536
|
| 22 |
- F1: 0.9933
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training and evaluation data
|
| 33 |
-
|
| 34 |
-
More information needed
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
|
|
|
|
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
|
@@ -62,4 +58,4 @@ The following hyperparameters were used during training:
|
|
| 62 |
- Transformers 4.48.0.dev0
|
| 63 |
- Pytorch 2.5.1+cu124
|
| 64 |
- Datasets 3.1.0
|
| 65 |
-
- Tokenizers 0.21.0
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: ModernBERT-large-llm-router
|
| 11 |
results: []
|
| 12 |
+
datasets:
|
| 13 |
+
- DevQuasar/llm_router_dataset-synth
|
| 14 |
+
pipeline_tag: text-classification
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
# ModernBERT-large-llm-router
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on [DevQuasar/llm_router_dataset-synth](https://huggingface.co/datasets/DevQuasar/llm_router_dataset-synth).
|
| 20 |
+
|
| 21 |
+
It achieves the following results on the test set:
|
| 22 |
- Loss: 0.0536
|
| 23 |
- F1: 0.9933
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
| 27 |
+
See original [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) model card for additional information. This model is intended to classify queries for LLM routing. More advanced queries get labeled 1 for large_llm and simpler queries get 0 for small_llm.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
Annotated training procedure available [in this notebook.](https://colab.research.google.com/drive/1G7oHp_8R4fmOSpjwaNB_T2NUJsmMh4Kw?usp=sharing) Methodology and code credits to [Phillip Schmid](https://huggingface.co/philschmid) from his [Fine-tune classifier with ModernBERT in 2025
|
| 32 |
+
](https://www.philschmid.de/fine-tune-modern-bert-in-2025) blog post.
|
| 33 |
+
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
|
|
|
| 58 |
- Transformers 4.48.0.dev0
|
| 59 |
- Pytorch 2.5.1+cu124
|
| 60 |
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.21.0
|