README.md

---
language:
- en
license: other
library_name: transformers
datasets:
- teknium/OpenHermes-2.5
- LDJnr/Capybara
- Intel/orca_dpo_pairs
- argilla/distilabel-capybara-dpo-7k-binarized
pipeline_tag: text-generation
model-index:
- name: Quyen-v0.1
  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: 48.21
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-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: 72.49
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-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: 52.88
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-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: 51.53
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-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: 65.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-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: 45.87
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-v0.1
      name: Open LLM Leaderboard
---

# Quyen
<img src="quyen.webp" width="512" height="512" alt="Quyen">

# Model Description
Quyen is our first flagship LLM series based on the Qwen1.5 family. We introduced 6 different versions:

- **Quyen-SE (0.5B)**
- **Quyen-Mini (1.8B)**
- **Quyen (4B)**
- **Quyen-Plus (7B)**
- **Quyen-Pro (14B)**
- **Quyen-Pro-Max (72B)**

All models were trained with SFT and DPO using the following dataset:

- *OpenHermes-2.5* by **Teknium**
- *Capyabara* by **LDJ**
- *argilla/distilabel-capybara-dpo-7k-binarized* by **argilla**
- *orca_dpo_pairs* by **Intel**
- and Private Data by **Ontocord** & **BEE-spoke-data**

# Prompt Template
- All Quyen models use ChatML as the default template:

```
<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Hello world.<|im_end|>
<|im_start|>assistant
```

- You can also use `apply_chat_template`:

```python
messages = [
    {"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."},
    {"role": "user", "content": "Hello world."}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
```

# Benchmarks:

- Coming Soon! We will update the benchmarks later

# Acknowledgement
- We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.
# [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_vilm__Quyen-v0.1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |56.02|
|AI2 Reasoning Challenge (25-Shot)|48.21|
|HellaSwag (10-Shot)              |72.49|
|MMLU (5-Shot)                    |52.88|
|TruthfulQA (0-shot)              |51.53|
|Winogrande (5-shot)              |65.11|
|GSM8k (5-shot)                   |45.87|