---
language:
- en
base_model: google/gemma-2-2b-it
datasets:
- BAAI/Infinity-Instruct
model-index:
- name: Gemma2-9B-IT-Simpo-Infinity-Preference
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 31.76
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 42.19
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 0.0
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 11.97
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 8.1
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 31.82
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
      name: Open LLM Leaderboard
---

## Overview
Gemma2-9B-IT-Simpo-Infinity-Preference is based on [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) and finetuned on [Infinity-Preference](https://huggingface.co/datasets/BAAI/Infinity-Preference) with [Simpo](https://github.com/princeton-nlp/SimPO). It achieves 73.4% LC win-rate on AlpacaEval 2.0 and 58.1% win-rate on Arena-Hard against GPT-4.

## Training hyperparameters

```yaml
beta: 10
gamma_beta_ratio: 1
learning_rate: 8.0e-7
log_level: info
logging_steps: 5
max_length: 2048
max_prompt_length: 1800
num_train_epochs: 1
batch_size: 128
```

## How to Use

Gemma2-9B-IT-Simpo-Infinity-Preference adopt the same chat template of [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it):

```bash
<bos><start_of_turn>user
How are you?<end_of_turn>
<start_of_turn>model
Hi!<end_of_turn>
```

To apply this model and template in conversation scenarios, you can refer to the following code:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, LogitsProcessorList
import torch
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference")

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

logits_processor = LogitsProcessorList(
            [
                MinLengthLogitsProcessor(1, eos_token_id=tokenizer.eos_token_id),
                TemperatureLogitsWarper(0.8),
            ]
 )
 
generated_ids = model.generate(
    model_inputs.input_ids,
    logits_processor=logits_processor,
    max_new_tokens=512
)

generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```

## Disclaimer

The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of Infinity-Preference is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BAAI__Gemma2-9B-IT-Simpo-Infinity-Preference)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |20.97|
|IFEval (0-Shot)    |31.76|
|BBH (3-Shot)       |42.19|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot)      |11.97|
|MuSR (0-shot)      | 8.10|
|MMLU-PRO (5-shot)  |31.82|