Upload LoRA backbone adapters

lora_backbone/README.md

@@ -1,46 +1,46 @@
----
-base_model: google/gemma-4-E2B-it
-library_name: peft
-tags:
-  - base_model:adapter:google/gemma-4-E2B-it
-  - lora
-  - peft
-  - classone
-  - decision-model
----
-
-# LoRA Adapter — classone-gemma4-e2b
-
-PEFT LoRA adapter for **[devops-thiago/classone-gemma4-e2b](https://huggingface.co/devops-thiago/classone-gemma4-e2b)**, the ClassOne System 1 decision model built on [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it).
-
-This subfolder holds only the low-rank adapter weights. The merged standalone weights live at the repository root, and the Noul / Choice / Score decision heads live in `classone_heads.pt` — load the heads alongside whichever backbone form you use.
-
-## Adapter Configuration
-
-| Setting | Value |
-|---|---|
-| Base model | `google/gemma-4-E2B-it` |
-| PEFT type | LORA |
-| Rank (r) | 16 |
-| `lora_alpha` | 32 |
-| `lora_dropout` | 0.05 |
-| Bias | none |
-| Target modules | `.*language_model.*(q_proj\|o_proj\|gate_proj\|up_proj\|down_proj).*` |
-| PEFT version | 0.21.0 |
-
-## Usage
-
-```python
-from peft import PeftModel
-from transformers import AutoModel
-
-base = AutoModel.from_pretrained("google/gemma-4-E2B-it")
-model = PeftModel.from_pretrained(base, "devops-thiago/classone-gemma4-e2b", subfolder="lora_backbone")
-```
-
-For end-to-end decision inference (packing questions, calibrated outputs), see the [model card](https://huggingface.co/devops-thiago/classone-gemma4-e2b).
-
-## Attribution & Legal
-
-- Base model: [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) (Google) — Apache License 2.0
-- Architecture: [devops-thiago/class-one](https://github.com/devops-thiago/class-one) — Apache 2.0
+---
+base_model: google/gemma-4-E2B-it
+library_name: peft
+tags:
+  - base_model:adapter:google/gemma-4-E2B-it
+  - lora
+  - peft
+  - classone
+  - decision-model
+---
+
+# LoRA Adapter — classone-gemma4-e2b
+
+PEFT LoRA adapter for **[devops-thiago/classone-gemma4-e2b](https://huggingface.co/devops-thiago/classone-gemma4-e2b)**, the ClassOne System 1 decision model built on [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it).
+
+This subfolder holds only the low-rank adapter weights. The merged standalone weights live at the repository root, and the Noul / Choice / Score decision heads live in `classone_heads.pt` — load the heads alongside whichever backbone form you use.
+
+## Adapter Configuration
+
+| Setting | Value |
+|---|---|
+| Base model | `google/gemma-4-E2B-it` |
+| PEFT type | LORA |
+| Rank (r) | 16 |
+| `lora_alpha` | 32 |
+| `lora_dropout` | 0.05 |
+| Bias | none |
+| Target modules | `.*language_model.*(q_proj\|o_proj\|gate_proj\|up_proj\|down_proj).*` |
+| PEFT version | 0.21.0 |
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModel
+
+base = AutoModel.from_pretrained("google/gemma-4-E2B-it")
+model = PeftModel.from_pretrained(base, "devops-thiago/classone-gemma4-e2b", subfolder="lora_backbone")
+```
+
+For end-to-end decision inference (packing questions, calibrated outputs), see the [model card](https://huggingface.co/devops-thiago/classone-gemma4-e2b).
+
+## Attribution & Legal
+
+- Base model: [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) (Google) — Apache License 2.0
+- Architecture: [devops-thiago/class-one](https://github.com/devops-thiago/class-one) — Apache 2.0