update model (super tiny now)

src/FineTune/ckpt/config.json

@@ -0,0 +1 @@
+{"domains": ["Academia", "Finance", "Government", "Knowledge", "Legislation", "Medicine", "News", "UserReview", "General"], "criterion": "mean"}

src/FineTune/ckpt/null_distrs.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54878910ccb7bcd7575dc032dccdd61e8ad604e5e195922c0051564ef8acd81
+size 3030341

src/FineTune/ckpt/scoring_model/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-3-1b-pt
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

src/FineTune/ckpt/scoring_model/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-pt",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

src/FineTune/ckpt/scoring_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74e22eead36ed3eef207c50d0ead88ea37f7748a0a0148be6dbc0a5d4701e37
+size 3009096

src/FineTune/model.py

@@ -90,9 +90,9 @@ class ComputeStat(nn.Module):
             self.peft_config = LoraConfig(
                 task_type=TaskType.CAUSAL_LM,
                 inference_mode=False,
-                r=8,
-                lora_alpha=32,
-                lora_dropout=0.1,
+                r=4,
+                lora_alpha=16,
+                lora_dropout=0.05,
                 target_modules=["q_proj", "k_proj", "v_proj", "o_proj"],
             )
         else:
@@ -138,15 +138,16 @@ class ComputeStat(nn.Module):
                 if selected_module in name:
                     param.requires_grad = False
 
-    def save_pretrained(self, save_directory: str):
+    def save_pretrained(self, save_directory: str, save_null_distr_only=False):
         """
         Save the scoring model (with LoRA adapter) and all null_distr buffers in Hugging Face format.
         """
         os.makedirs(save_directory, exist_ok=True)
 
         # 1. 保存 scoring_model (LoRA adapter + 基础模型)
-        scoring_dir = os.path.join(save_directory, "scoring_model")
-        self.scoring_model.save_pretrained(scoring_dir, safe_serialization=True)
+        if not save_null_distr_only:
+            scoring_dir = os.path.join(save_directory, "scoring_model")
+            self.scoring_model.save_pretrained(scoring_dir, safe_serialization=True)
 
         # 2. 保存所有 null_distr_* buffers
         null_distrs = {}

src/app.py

@@ -52,7 +52,8 @@ def load_model(from_pretrained, base_model, cache_dir, device):
     Load and cache the model to avoid reloading on every user interaction.
     This function runs only once when the app starts or when parameters change.
     """
-    is_hf_space = os.environ.get('SPACE_ID') is not None
+    # is_hf_space = os.environ.get('SPACE_ID') is not None
+    is_hf_space = False
     if is_hf_space:
         cache_dir = '/tmp/huggingface_cache'
         os.makedirs(cache_dir, exist_ok=True)
@@ -98,7 +99,6 @@ def load_model(from_pretrained, base_model, cache_dir, device):
         model = ComputeStat.from_pretrained(
             from_pretrained, 
             base_model, 
-            base_model, 
             device=device,
             cache_dir=cache_dir
         )
@@ -158,10 +158,12 @@ def save_feedback(text, domain, statistics, p_value, feedback_type):
 # Configuration
 # -----------------
 MODEL_CONFIG = {
-    'from_pretrained': 'mamba413/AdaDetectGPT-Model' if os.environ.get('SPACE_ID') else './src/FineTune/ckpt/lr_0.0001_a_1',
+    # 'from_pretrained': 'mamba413/AdaDetectGPT-Model' if os.environ.get('SPACE_ID') else './src/FineTune/ckpt/lr_0.0001_a_1',
+    'from_pretrained': './src/FineTune/ckpt/',
     'base_model': 'gemma-1b',
     'cache_dir': '../cache', 
-    'device': 'mps',
+    # 'device': 'mps',
+    'device': 'cpu',
     # 'device': 'cuda',
 }