language:
- en
license: cc-by-4.0
library_name: transformers
tags:
- llm
- 7b
datasets:
- argilla/distilabel-math-preference-dpo
model-index:
- name: jaskier-7b-dpo-v5.6
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: 73.04
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
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: 89
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
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: 64.38
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
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: 77.81
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
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: 84.53
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
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: 69.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bardsai/jaskier-7b-dpo-v5.6
name: Open LLM Leaderboard
Jaskier-7b-dpo-v5.6
This is work-in-progress model, may not be ready for production use
Model based on paulml/OGNO-7B (downstream version of Mistral7B) finetuned using Direct Preference Optimization on argilla/distilabel-math-preference-dpo.
How to use
You can use this model directly with a Hugging Face pipeline:
from transformers import pipeline, Conversation
import torch
base_model_name = "bardsai/jaskier-7b-dpo-v5.6"
chatbot = pipeline("conversational", model=base_model_name, torch_dtype=torch.float16, device_map="auto")
conversation = Conversation("Is bard an ML engineer?")
conversation = chatbot(conversation)
print(conversation.messages[-1]["content"])
Output
"There is no direct personal connection between the concept of a "bard" and an "ML engineer." A bard is a mythical or literary figure, often a storyteller or musician, while an ML engineer refers to a Machine Learning engineer, a professional in the tech industry. They are unrelated entities, one fictional and the other a real-world occupation."
If you still find any issues with "INST" character chain appearing in generated output, try our newest model: https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1 . Re-tasking the prompt can also help.
Changelog
- 2024-02-16: Initial release
About bards.ai
At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: bards.ai
Let us know if you use our model :). Also, if you need any help, feel free to contact us at info@bards.ai
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 76.41 |
| AI2 Reasoning Challenge (25-Shot) | 73.04 |
| HellaSwag (10-Shot) | 89.00 |
| MMLU (5-Shot) | 64.38 |
| TruthfulQA (0-shot) | 77.81 |
| Winogrande (5-shot) | 84.53 |
| GSM8k (5-shot) | 69.67 |