Add model card with benchmark results

README.md

@@ -14,7 +14,7 @@ pipeline_tag: text-classification
 
 # classone-gemma4-e2b — ClassOne System 1 Decision Model
 
-**[devops-thiago/classone-gemma4-e2b](https://huggingface.co/devops-thiago/classone-gemma4-e2b)** is an open-source **System 1 decision model** built on top of [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) using the [ClassOne architecture](https://github.com/devops-thiago/class-one).
+**[devops-thiago/classone-gemma4-e2b](https://huggingface.co/devops-thiago/classone-gemma4-e2b)** is an open-source **System 1 decision model** using the [ClassOne architecture](https://github.com/devops-thiago/class-one). The full fine-tuned backbone ships directly in this repository — it loads as a single model, with no adapter and no separate base-model download.
 
 Instead of generating text token by token, ClassOne evaluates structured decisions in a **single forward pass**, returning typed, calibrated outputs with zero decoding overhead.
 
@@ -82,7 +82,6 @@ pip install classone
 ```python
 import torch
 from huggingface_hub import hf_hub_download
-from peft import PeftModel
 from transformers import AutoTokenizer
 
 from classone.modeling.modeling_classone import ClassOneModel
@@ -91,16 +90,15 @@ from classone.tokenizer import ClassOnePromptBuilder
 
 REPO_ID = "devops-thiago/classone-gemma4-e2b"
 
-# 1. Load the backbone and attach the published LoRA adapter
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-E2B-it")
+# 1. Load the ClassOne model (weights + tokenizer are fully self-contained here)
+tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
 builder = ClassOnePromptBuilder(tokenizer)
 model = ClassOneModel.from_backbone(
-    base_model_name_or_path="google/gemma-4-E2B-it",
+    base_model_name_or_path=REPO_ID,
     tokenizer=tokenizer,
     device="cuda",
     torch_dtype=torch.float16,
 )
-model.backbone = PeftModel.from_pretrained(model.backbone, REPO_ID, subfolder="lora_backbone")
 
 # 2. Load the trained decision heads
 heads = torch.load(hf_hub_download(REPO_ID, "classone_heads.pt"), map_location="cuda")
@@ -135,9 +133,11 @@ print("Anger score:   ", results["anger"].score)
 
 | File | Description |
 |---|---|
+| `model.safetensors` (sharded) | Merged ClassOne backbone weights |
+| `config.json` | Model configuration |
+| `tokenizer.json`, `tokenizer_config.json` | Tokenizer, including ClassOne delimiter tokens |
 | `classone_heads.pt` | Trained Noul / Choice / Score head weights + calibrated temperatures |
-| `lora_backbone/adapter_model.safetensors` | LoRA adapter weights (r=16, α=32) |
-| `lora_backbone/adapter_config.json` | LoRA config (target modules, rank, etc.) |
+| `lora_backbone/` | LoRA adapter (r=16, α=32) that produced the merged weights |
 
 ## Citation