from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# 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">🥇 Test Space</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Leaderboards for LLM evaluation.

*TRUE(Trustworthy Real-world Usage Evaluation)Bench* is designed to evaluate LLMs for Productivity Assistants which stand for human's job productivity.
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works
We utilize LLM Judge with human-crafted criteria to assess AI response.
"""

EVALUATION_QUEUE_TEXT = """
## Submission Policy
For each benchmark:
1. Each model affiliation (individual or organization) can submit up to 3 times within 24 hours.
2. The same model can only be submitted once within 24 hours.
3. Criteria for determining duplicate submissions:
    - Benchmark name
    - Model full name
    - Sampling parameters, dtype, vLLM version, etc. are not subject to duplicate checking.
4. Submissions are only allowed if the model's organization or username matches that of the submitter.

## 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
"""

EVALUATION_QUEUE_TEXT_OPTION1 = """
# (Option 1) Submit HF model where vLLM inference is available
1. Fill the information including model name, vLLM version, sampling hyperparameters.
2. Sign in using the log-in button below.
3. Press "Submit Eval" button to submit.
"""

EVALUATION_QUEUE_TEXT_OPTION2 = """
# (Option 2) Submit HF model where vLLM inference is unavailable
1. Fill the information same with Option 1 and code snippets of model loading, inference, and termination.
2. Sign in using the log-in button below.
3. Press "Submit Eval" button to submit.
"""

EVALUATION_QUEUE_TEXT_OPTION3 = """
# (Option 3) Pull Request
If Option 1 & 2 is unavailable, make [PR](https://huggingface.co/spaces/coms1580/test_space/discussions?new_pr=true) with [ADD_MODEL] prefix with contents as follows:

```
### Open-weight models:
- Benchmark Name: [The name of benchmark to be evaluated]
- HugingFace Model ID: [HF_MODEL_ID]
- Pretty Name: [PRETTY_NAME]
- Sampling parameters:
    - Temperature
    - Top-p
    - Top-k
    - Presence penalty
    - Frequency penalty
    - Repetition penalty
- Supported by vLLM: [yes/no]
- (If yes) Version of vLLM
- (If no) Code snippets:
    - Model loading
    - Inference
    - Termination

### Misc. 
- Contact: [your email]
- Description: [e.g.,  paper link, blog post, etc.]
- Notes: [optional]
```
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
"""