Evangelion-7B/README.md

license, library_name, datasets, pipeline_tag, model-index

license	library_name	datasets	pipeline_tag	model-index
apache-2.0	transformers	argilla/distilabel-intel-orca-dpo-pairs	text-generation	name results Evangelion-7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 68.94 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 86.45 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 63.97 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 64.01 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 79.95 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 66.94 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=VitalContribution/Evangelion-7B Open LLM Leaderboard

🌐 Company Website 🔗 Mozaic AI Solutions

---

✨ Overview

We were curious to see what happens if one uses:

\text{{high-quality DPO dataset}} + \text{{merge of DPO optimized and non-DPO optimized model}}

The underlying model used was:
/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

---

Dataset

Dataset: /argilla/distilabel-intel-orca-dpo-pairs

The dataset was roughly ~3000 samples but they were high quality (according to the chosen_score).
The following filters were applied to the original dataset:

dataset = dataset.filter(
    lambda r:
        r["status"] != "tie" and
        r["chosen_score"] >= 8 and
        not r["in_gsm8k_train"]
)

Chat Template

I decided to go with the ChatML which is used for OpenHermes2.5 By the way I integreated the chat template into the models tokenizer.

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.71
AI2 Reasoning Challenge (25-Shot)	68.94
HellaSwag (10-Shot)	86.45
MMLU (5-Shot)	63.97
TruthfulQA (0-shot)	64.01
Winogrande (5-shot)	79.95
GSM8k (5-shot)	66.94