---
language:
- ja
- en
license: cc-by-4.0
datasets:
- cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental
base_model: cyberagent/calm2-7b-chat
model-index:
- name: calm2-7b-chat-dpo-experimental
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 41.04
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 68.99
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 39.82
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 43.13
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 65.67
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 5.53
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cyberagent/calm2-7b-chat-dpo-experimental
      name: Open LLM Leaderboard
---

# Model Card for "calm2-7b-chat-dpo-experimental"

[cyberagent/calm2-7b-chat](https://huggingface.co/cyberagent/calm2-7b-chat)に[cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental](https://huggingface.co/datasets/cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental)データセットを用いて[Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290)をしたモデルです。
DPOには[Low-Rank Adaptation (LoRA)](https://huggingface.co/docs/peft/conceptual_guides/lora)を用いました。

## Requirements, Usage, Chat Template

[cyberagent/calm2-7b-chat](https://huggingface.co/cyberagent/calm2-7b-chat)と同様です。
同様のコード・プロンプトで動かすことができます。

```python
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

assert transformers.__version__ >= "4.34.1"

model = AutoModelForCausalLM.from_pretrained("cyberagent/calm2-7b-chat-dpo-experimental", device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm2-7b-chat-dpo-experimental")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = """USER: AIによって私達の暮らしはどのように変わりますか？
ASSISTANT: """

token_ids = tokenizer.encode(prompt, return_tensors="pt")
output_ids = model.generate(
    input_ids=token_ids.to(model.device),
    max_new_tokens=300,
    do_sample=True,
    temperature=0.8,
    streamer=streamer,
)
```

## 実験結果

### ELYZA-tasks-100 (GPT-4 eval)

実験結果のランダム性を避けるため、greedy searchで出力しました。

| calm2-7b-chat | calm2-7b-chat-dpo |
| ---- | ---- | 
| 2.67 | 2.85 |


### Japanese MT-Bench

以下の文をシステムプロンプト（system_message）としてcalm2-7b-chat-dpoとcalm2-7b-chatの評価を行いました。

"以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。"

このシステムプロンプトは[stabilityai/japanese-stablelm-instruct-alpha-7bを評価するときに使われるもの](https://github.com/Stability-AI/FastChat/blob/dfb653d2cadd16017b66bbc3a25cf361031f2da3/fastchat/conversation.py#L364)をそのまま使いました。
他のデコーディングパラメータはデフォルトのままです（ランダム性があります）。

| | calm2-7b-chat | calm2-7b-chat-dpo |
| ---- | ---- | ---- | 
| 平均 | 6.1 | 6.7 |
| extraction |	4.1	| 5.4 |
| humanities	| 8.2	| 8.4 |
| reasoning	| 3.9	| 4.3 |
| roleplay	| 6.4	| 7.0 |
| stem	| 6.3	| 6.2 |
| writing	| 7.7	| 9.1 |

## Releases

1.0: v1 release (Jan 24, 2024)

## Author

Yuu Jinnai (jinnai_yu@cyberagent.co.jp), Standing on the shoulders of giants
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cyberagent__calm2-7b-chat-dpo-experimental)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |44.03|
|AI2 Reasoning Challenge (25-Shot)|41.04|
|HellaSwag (10-Shot)              |68.99|
|MMLU (5-Shot)                    |39.82|
|TruthfulQA (0-shot)              |43.13|
|Winogrande (5-shot)              |65.67|
|GSM8k (5-shot)                   | 5.53|