Card
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
|
|
|
| 3 |
tags:
|
| 4 |
- evalexplorer
|
| 5 |
- document-classification
|
|
@@ -8,7 +9,8 @@ tags:
|
|
| 8 |
|
| 9 |
# evalexplorer-classify-adapters
|
| 10 |
|
| 11 |
-
Experimental LoRA adapters for the EvalExplorer document classifier, one subfolder per run.
|
|
|
|
| 12 |
on their own get their own repo (`baobabtech/evalexplorer-classify-<model>-sft`); variants from GRPO and other
|
| 13 |
trials live here so they do not each need one. Each subfolder holds `adapter_config.json`,
|
| 14 |
`adapter_model.safetensors`, the tokenizer and `training_log.json`.
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- evalexplorer
|
| 6 |
- document-classification
|
|
|
|
| 9 |
|
| 10 |
# evalexplorer-classify-adapters
|
| 11 |
|
| 12 |
+
Experimental LoRA adapters for the EvalExplorer document classifier, one subfolder per run. Every adapter here is
|
| 13 |
+
on an Apache-2.0 base (Qwen3.5, Gemma 4); each keeps its base model's terms. Adapters worth using
|
| 14 |
on their own get their own repo (`baobabtech/evalexplorer-classify-<model>-sft`); variants from GRPO and other
|
| 15 |
trials live here so they do not each need one. Each subfolder holds `adapter_config.json`,
|
| 16 |
`adapter_model.safetensors`, the tokenizer and `training_log.json`.
|