Hugging Face's logo

robinsmits
/
Qwen1.5-7B-Dutch-Chat

Text Generation
Transformers
Safetensors
Dutch
qwen2
trl
dpo
conversational
Eval Results
text-generation-inference
Model card Files Community
1
Qwen1.5-7B-Dutch-Chat / README.md
robinsmits's picture
robinsmits
Adding Evaluation Results
3ffd510 verified
preview code
|
raw
history blame
10.2 kB
metadata
language:
  - nl
license: cc-by-nc-4.0
library_name: transformers
tags:
  - trl
  - dpo
  - conversational
datasets:
  - BramVanroy/ultra_feedback_dutch_cleaned
pipeline_tag: text-generation
inference: false
model-index:
  - name: Qwen1.5-7B-Dutch-Chat
    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: 53.92
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          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: 76.03
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          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: 62.38
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          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: 45.34
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          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: 68.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          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: 15.47
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Qwen1.5-7B-Dutch-Chat
          name: Open LLM Leaderboard

Qwen1.5-7B-Dutch-Chat

Model description

This DPO aligned model is the merged version of the adapter model robinsmits/Qwen1.5-7B-Dutch-Chat-Dpo.

DPO Finetuning was performed on the Dutch BramVanroy/ultra_feedback_dutch_cleaned dataset.

See Qwen/Qwen1.5-7B-Chat for all information about the base model.

Model usage

A basic example of how to use the finetuned model.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

device = 'cuda'
model_name = 'robinsmits/Qwen1.5-7B-Dutch-Chat'

model = AutoModelForCausalLM.from_pretrained(model_name, 
                                             device_map = "auto", 
                                             torch_dtype = torch.bfloat16)

tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [{"role": "user", "content": "Hoi hoe gaat het ermee? Wat kun je me vertellen over appels?"}]

encoded_ids = tokenizer.apply_chat_template(messages, 
                                            add_generation_prompt = True,
                                            return_tensors = "pt")

generated_ids = model.generate(input_ids = encoded_ids.to(device), 
                               max_new_tokens = 256,
                               do_sample = True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Below the chat template with the generated output.

<|im_start|>system
Je bent een behulpzame AI assistent<|im_end|>
<|im_start|>user
Hoi hoe gaat het ermee? Wat kun je me vertellen over appels?<|im_end|>
<|im_start|>assistant
Hallo! Appels zijn zo'n lekkere fruitsoort. Ze zijn zoet en knapperig, en je kunt ze koken, roosteren of zelfs in smoothies doen. Er zijn heel veel verschillende soorten appels, zoals de Fuji, Granny Smith en Gala. De appels die je meestal in de winkel koopt, komen van bomen die in het oosten van Noord-Amerika groeien.<|im_end|>

Intended uses & limitations

As with all LLM's this model can also experience bias and hallucinations. Regardless of how you use this model always perform the necessary testing and validation.

The used dataset does not allow commercial usage.

Training and evaluation data

The training notebook is available at the following link: Qwen1_5_7B_Dutch_Chat_DPO

Training was performed with Google Colab PRO on a A100 - 40GB and lasted around 4 hours.

It achieves the following results on the evaluation set:

  • Loss: 0.2610
  • Rewards/chosen: -0.7248
  • Rewards/rejected: -2.6224
  • Rewards/accuracies: 0.9170
  • Rewards/margins: 1.8976
  • Logps/rejected: -877.8102
  • Logps/chosen: -783.4282
  • Logits/rejected: -0.8110
  • Logits/chosen: -0.7528

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
0.5503 0.1 30 0.4684 -0.0439 -0.6295 0.8919 0.5856 -837.9513 -769.8103 -0.9335 -0.8894
0.4178 0.2 60 0.3568 -0.3713 -1.4769 0.9015 1.1056 -854.9000 -776.3594 -0.8768 -0.8276
0.3264 0.29 90 0.3143 -0.4893 -1.8730 0.9151 1.3837 -862.8228 -778.7191 -0.8428 -0.7929
0.2999 0.39 120 0.2885 -0.6832 -2.3118 0.9151 1.6286 -871.5981 -782.5971 -0.8260 -0.7730
0.3454 0.49 150 0.2749 -0.7239 -2.4904 0.9189 1.7664 -875.1693 -783.4113 -0.8235 -0.7678
0.3354 0.59 180 0.2685 -0.6775 -2.4859 0.9170 1.8084 -875.0795 -782.4824 -0.8130 -0.7574
0.2848 0.68 210 0.2652 -0.7157 -2.5692 0.9131 1.8535 -876.7465 -783.2466 -0.8157 -0.7586
0.3437 0.78 240 0.2621 -0.7233 -2.6091 0.9151 1.8857 -877.5430 -783.3994 -0.8138 -0.7561
0.2655 0.88 270 0.2611 -0.7183 -2.6154 0.9151 1.8971 -877.6708 -783.2995 -0.8106 -0.7524
0.3442 0.98 300 0.2610 -0.7248 -2.6224 0.9170 1.8976 -877.8102 -783.4282 -0.8110 -0.7528

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2

Citation

Thanks to the creators of Qwen1.5 for there great work!

@article{qwen,
  title={Qwen Technical Report},
  author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
  journal={arXiv preprint arXiv:2309.16609},
  year={2023}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 53.66
AI2 Reasoning Challenge (25-Shot) 53.92
HellaSwag (10-Shot) 76.03
MMLU (5-Shot) 62.38
TruthfulQA (0-shot) 45.34
Winogrande (5-shot) 68.82
GSM8k (5-shot) 15.47