perlthoughts/neural-chat-v3-3-8x7b-MoE

Intel's Neural Chat v3-3 8x7B Mixtral MOE

Original Model Details: Neural-Chat-v3-3

This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the Intel/neural-chat-7b-v3-1 on the meta-math/MetaMathQA dataset. The model was aligned using the Direct Performance Optimization (DPO) method with Intel/orca_dpo_pairs. The Intel/neural-chat-7b-v3-1 was originally fine-tuned from mistralai/Mistral-7B-v-0.1. For more information, refer to our blog The Practice of Supervised Fine-tuning and Direct Preference Optimization on Intel Gaudi2.

Note: Adjust lora modules to trade off truthfulqa and gsm8k performance on DPO stage.

Model Detail	Description
Model Authors - Company	Intel. The NeuralChat team with members from Intel/DCAI/AISE/AIPT. Core team members: Kaokao Lv, Liang Lv, Chang Wang, Wenxin Zhang, Xuhui Ren, and Haihao Shen.
Date	December, 2023
Version	v3-3
Type	7B Large Language Model
Paper or Other Resources	Medium Blog
License	Apache 2.0
Questions or Comments	Community Tab and Intel Developers Discord

Intended Use	Description
Primary intended uses	You can use the fine-tuned model for several language-related tasks. Checkout the LLM Leaderboard to see how this model and others from Intel are doing.
Primary intended users	Anyone doing inference on language-related tasks.
Out-of-scope uses	This model in most cases will need to be fine-tuned for your particular task. The model should not be used to intentionally create hostile or alienating environments for people.

How to use and Sample Code

Here is the sample code to reproduce the model: Sample Code.

Prompt Template

### System:
{system}
### User:
{usr}
### Assistant:

Quantitative Analyses: Open LLM Leaderboard Evaluation Results

Detailed results can be found here (note: the leaderboard removed drop task)

Metric	Value
Avg.	69.83
ARC (25-shot)	66.89
HellaSwag (10-shot)	85.26
MMLU (5-shot)	63.07
TruthfulQA (0-shot)	63.01
Winogrande (5-shot)	79.64
GSM8K (5-shot)	61.11

Useful links

• Intel Neural Compressor link
• Intel Extension for Transformers link

Ethical Considerations and Limitations

neural-chat-7b-v3-3 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of neural-chat-7b-v3-3, developers should perform safety testing.

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.17
AI2 Reasoning Challenge (25-Shot)	66.64
HellaSwag (10-Shot)	85.43
MMLU (5-Shot)	62.22
TruthfulQA (0-shot)	63.20
Winogrande (5-shot)	79.72
GSM8k (5-shot)	69.83