README.md

---
language:
- ja
- en
license: other
library_name: transformers
tags:
- llama
- llama-2
- steerlm
datasets:
- OpenAssistant/oasst2
- nvidia/HelpSteer
base_model: karakuri-ai/karakuri-lm-70b-v0.1
pipeline_tag: conversational
model-index:
- name: karakuri-ai/karakuri-lm-70b-chat-v0.1
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MT-Bench
      type: unknown
    metrics:
    - type: unknown
      value: 6.609375
      name: score
    - type: unknown
      value: 6.43125
      name: score
    source:
      url: https://huggingface.co/spaces/lmsys/mt-bench
  - 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: 61.52
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      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: 83.13
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      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: 59.35
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      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: 51.39
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      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: 78.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      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: 40.41
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=karakuri-ai/karakuri-lm-70b-chat-v0.1
      name: Open LLM Leaderboard
---

# KARAKURI LM

![KARAKURI LM](./thumbnail.png)

KARAKURI LM is a pretrained language model that builds upon Llama 2.
Our model enhances Llama 2's capabilities by incorporating additional Japanese vocabulary and further pretraining on a mixture of Japanese and multilingual corpora.

KARAKURI LM Chat is a fine-tuned version of KARAKURI LM, which was trained on a mixture of publicly available and closed datasets using the [SteerLM](https://aclanthology.org/2023.findings-emnlp.754/) technique.
During fine-tuning, our model employed a continual learning approach.
Unlike the common practice of relying solely on structured conversational datasets, we also incorporated unstructured corpora, similar to what was used during its pretraining phase.

Despite the conversational datasets containing only 2.5% Japanese tokens, our model has shown remarkable performance.
It achieves the highest performance among Japanese open models on the [MT-Bench-jp](https://api.wandb.ai/links/wandb-japan/6ff86bp3) at the time of release.
Furthermore, it achieves performance comparable to Llama 2 70B Chat on the original English [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench).

You can find more details in our blog post ([en](https://medium.com/karakuri/introducing-karakuri-lm-34c79a3bf341), [ja](https://medium.com/karakuri/karakuri-lm%E3%81%AE%E8%A7%A3%E8%AA%AC-4b6cf9c3d40f)).
If you are curious about our model, give our [demo](https://lm.karakuri.cc/) a try.

## Model Details

- **Developed by**: [KARAKURI Inc.](https://about.karakuri.ai/)
- **Model type**: Causal decoder-only transformer language model
- **Languages**: English and Japanese
- **Finetuned from**: [karakuri-ai/karakuri-lm-70b-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-70b-v0.1)
- **Contact**: For questions and comments about the model, please email `karakuri-rd@karakuri.ai`

## Performance

At the time of release, KARAKURI LM 70B Chat v0.1 achieves the highest performance among Japanese open models on the [MT-Bench-jp](https://api.wandb.ai/links/wandb-japan/6ff86bp3):

| Model                               |  Size   |  Alignment  | MT-Bench-jp |
| :---------------------------------- | :-----: | :---------: | ----------: |
| GPT-4                               |    -    |    RLHF     |        8.78 |
| GPT-3.5-Turbo                       |    -    |    RLHF     |        8.24 |
| Claude 2.1                          |    -    |    RLHF     |        8.18 |
| Gemini Pro                          |    -    |    RLHF     |        7.17 |
| **KARAKURI LM 70B Chat v0.1**       | **70B** | **SteerLM** |    **6.43** |
| Qarasu-14B-Chat-Plus-Unleashed      |   14B   |     SFT     |        6.26 |
| Llama 2 70B Chat                    |   70B   |    RLHF     |        5.23 |
| ELYZA-Japanese-Llama-2-13B          |   13B   |     SFT     |        5.05 |
| Japanese-StableLM-Instruct-Beta-70B |   70B   |     SFT     |        5.03 |
| Swallow-70B-Instruct                |   70B   |     SFT     |        4.39 |

It also achieves performance comparable to Llama 2 70B Chat on the original English [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench):

| Model                         |  Average | MT-Bench | MT-Bench-jp |
| :---------------------------- | -------: | -------: | ----------: |
| **KARAKURI LM 70B Chat v0.1** | **6.52** | **6.61** |    **6.43** |
| Llama 2 70B Chat              |     6.04 |     6.86 |        5.23 |

## Use in 🤗 Transformers

You can run the model using the `pipeline()` function from 🤗 Transformers:

```python
from transformers import pipeline, Conversation

chatbot = pipeline("conversational", model="karakuri-ai/karakuri-lm-70b-chat-v0.1", device_map="auto", torch_dtype="auto")

conversation = Conversation("週末に日帰りで東京に遊びに行こうと思っています。日帰りなので、短時間で回れるおすすめの観光プランを教えてください。")
conversation = chatbot(conversation, max_new_tokens=512)
conversation.messages[-1]["content"]
```

We use the following prompt template of multi-turn conversation in the Llama format, which includes an encoded string of multiple attribute values.

```python
messages = [
    {"role": "system", "content": "System prompt"},
    {"role": "user", "content": "User prompt"},
    {"role": "assistant", "content": "Model response"},
    {"role": "user", "content": "User prompt"},
]
chatbot.tokenizer.apply_chat_template(messages, tokenize=False)
# <s>[INST] <<SYS>>
# System prompt
# <</SYS>>
#
# User prompt [ATTR] helpfulness: 4 correctness: 4 coherence: 4 complexity: 4 verbosity: 4 quality: 4 toxicity: 0 humor: 0 creativity: 0 [/ATTR] [/INST] Model response </s><s>[INST] User prompt [ATTR] helpfulness: 4 correctness: 4 coherence: 4 complexity: 4 verbosity: 4 quality: 4 toxicity: 0 humor: 0 creativity: 0 [/ATTR] [/INST]
```

The prompt template contains nine attributes.
The first five are derived from HelpSteer, while the remaining four are derived from OASST2.
The values are represented by integers ranging from 0 to 4, with 0 being the lowest and 4 being the highest.

- helpfulness (default: 4)
- correctness (default: 4)
- coherence (default: 4)
- complexity (default: 4)
- verbosity (default: 4)
- quality (default: 4)
- toxicity (default: 0)
- humor (default: 0)
- creativity (default: 0)

You can change the attribute values by replacing the default values specified in the chat template:

```python
chatbot.tokenizer.chat_template = chatbot.tokenizer.chat_template.replace("complexity: 4", "complexity: 0")
```

## Training

### Training Datasets

- [OASST2](https://huggingface.co/datasets/OpenAssistant/oasst2)
- Our internal conversational datasets

### Training Infrastructure

- **Hardware**: KARAKURI LM 70B was trained on 32 nodes of an Amazon EC2 trn1.32xlarge instance.
- **Software**: We use code based on [neuronx-nemo-megatron](https://github.com/aws-neuron/neuronx-nemo-megatron).

## Acknowledgements

We gratefully acknowledge the support from AWS Japan through the [AWS LLM Development Support Program](https://aws.amazon.com/jp/local/llm-development-support-program/).

## License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

Subject to the license above, and except for commercial purposes, you are free to share and adapt KARAKURI LM, provided that you must, in a recognizable and appropriate manner, (i) state that you are using KARAKURI LM developed by KARAKURI Inc., when you publish or make available to third parties KARAKURI LM, its derivative works or modification, or any output or results of KARAKURI LM or its derivative works or modification, and (ii) indicate your contributions, if you modified any material of KARAKURI LM.


If you plan to use KARAKURI LM for commercial purposes, please contact us beforehand. You are not authorized to use KARAKURI LM for commercial purposes unless we expressly grant you such rights. 

If you have any questions regarding the interpretation of above terms, please also feel free to contact us.

# [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_karakuri-ai__karakuri-lm-70b-chat-v0.1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |62.36|
|AI2 Reasoning Challenge (25-Shot)|61.52|
|HellaSwag (10-Shot)              |83.13|
|MMLU (5-Shot)                    |59.35|
|TruthfulQA (0-shot)              |51.39|
|Winogrande (5-shot)              |78.37|
|GSM8k (5-shot)                   |40.41|