Mozaic-7B

We were curious to see what happens if one uses: $$\text{high-quality DPO dataset}+\text{merge of DPO optimized and non-DPO optimized model}\backslash text\{\{high-quality\; DPO\; dataset\}\}\; +\; \backslash text\{\{merge\; of\; DPO\; optimized\; and\; non-DPO\; optimized\; model\}\}$$

The underlying model that I 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