Create report.py

src/report.py

@@ -0,0 +1,120 @@
+from dataclasses import dataclass
+from enum import Enum
+from pathlib import Path
+@dataclass
+class Task:
+    benchmark: str
+    metric: str
+    col_name: str
+REPORT_MD_PATH = Path(__file__).parent.parent / "Files" / "report.md"
+with open(REPORT_MD_PATH, "r", encoding="utf-8") as f:
+    REPORT_TEXT = f.read()
+
+TITLE = "# LLM Benchmark Leaderboard"
+
+# 替换LLM_BENCHMARKS_TEXT为report.md内容
+LLM_BENCHMARKS_TEXT = REPORT_TEXT
+
+CITATION_BUTTON_LABEL = "📖 Citation"
+CITATION_BUTTON_TEXT = """If you use this benchmark, please cite: ...
+(原citation内容保留)"""
+
+EVALUATION_QUEUE_TEXT = "Models submitted for evaluation will appear here."
+
+
+# Select your tasks here
+# ---------------------------------------------------
+class Tasks(Enum):
+    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
+    task0 = Task("anli_r1", "acc", "ANLI")
+    task1 = Task("logiqa", "acc_norm", "LogiQA")
+
+NUM_FEWSHOT = 0 # Change with your few shot
+# ---------------------------------------------------
+
+
+
+# Your leaderboard name
+TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+
+# What does your leaderboard evaluate?
+INTRODUCTION_TEXT = """
+Intro text
+"""
+
+# Which evaluations are you running? how can people reproduce what you have?
+LLM_BENCHMARKS_TEXT = f"""
+## How it works
+
+## Reproducibility
+To reproduce our results, here is the commands you can run:
+
+"""
+
+EVALUATION_QUEUE_TEXT = """
+## Some good practices before submitting a model
+
+### 1) Make sure you can load your model and tokenizer using AutoClasses:
+```python
+from transformers import AutoConfig, AutoModel, AutoTokenizer
+config = AutoConfig.from_pretrained("your model name", revision=revision)
+model = AutoModel.from_pretrained("your model name", revision=revision)
+tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
+```
+If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
+
+Note: make sure your model is public!
+Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
+
+### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
+It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
+
+### 3) Make sure your model has an open license!
+This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
+
+### 4) Fill up your model card
+When we add extra information about models to the leaderboard, it will be automatically taken from the model card
+
+## In case of model failure
+If your model is displayed in the `FAILED` category, its execution stopped.
+Make sure you have followed the above steps first.
+If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
+"""
+
+CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
+CITATION_BUTTON_TEXT = r"""
+"""
+# Report
+
+## 1. 模型及类别选择
+
+本次实验选用了三类大模型：Llama 3, Mistral 7B, ChatGPT。
+
+- **Llama 3**：开源社区广泛使用，适合中英文任务。
+- **Mistral 7B**：轻量级，适合边缘设备。
+- **ChatGPT**：闭源，适合通用对话任务，表现最优。
+
+| 模型名称   | 参数量 | 开源情况 | 主要用途         |
+|------------|--------|---------|----------------|
+| Llama 3    | 70B    | 是      | 多语言任务       |
+| Mistral 7B | 7B     | 是      | 低功耗推理任务   |
+| ChatGPT    | 未公开 | 否      | 通用对话、推理任务 |
+
+**选择理由**：
+- Llama 3和Mistral为开源，方便定制与修改；
+- ChatGPT性能优越，作为基准。
+
+---
+
+## 2. 系统实现细节
+
+### Gradio交互界面截图
+![Gradio界面](./interface.png)
+
+### 输入与输出流程图
+```mermaid
+graph TD
+    A[用户输入] --> B[Gradio界面]
+    B --> C[模型推理]
+    C --> D[返回结果]
+