spmurrayzzz/Mistral-Syndicate-7B

Mistral-Syndicate-7B

<img src="https://cdn-uploads.huggingface.co/production/uploads/64712903631bb7660aaa7183/yMzb5tbgygtlHnoyR37YO.png" width="600px" />

Model Description:

Mistral Syndicate is in no way a state-of-the-art model, rather it is a fine-tuning experiment to explore the training dynamics specific to large language models. The dataset used in finetuning was generated via a "syndicate" of other open language models both of similar parameter size and larger. Each model would generate a response for a given instruction, and the group would vote on which model's response was best.

The instruction inputs used for the output label synthesis were a curated subset of VMWare/open-instruct with additional instructions synthesized from scratch.

Prompt template

With context

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:

### Input:

### Response:

Without context

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:

### Response:

Evaluation Results

12.30.23 | Benchmark | Result | |------------|--------| | ARC | 60.84 | | HellaSwag | 82.91 | | MMLU | 60.83 | | TruthfulQA | 43.71 | | Winogrande | 78.61 | | GSM8K | 44.50 |

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Open LLM Leaderboard Evaluation Results

Detailed results can be found here