metadata
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-Mini-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: 39.33
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-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: 60.57
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-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: 43.93
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-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: 46.44
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-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: 59.12
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-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: 27.45
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vilm/Quyen-Mini-v0.1
name: Open LLM Leaderboard
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:
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
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 46.14 |
| AI2 Reasoning Challenge (25-Shot) | 39.33 |
| HellaSwag (10-Shot) | 60.57 |
| MMLU (5-Shot) | 43.93 |
| TruthfulQA (0-shot) | 46.44 |
| Winogrande (5-shot) | 59.12 |
| GSM8k (5-shot) | 27.45 |