README.md

---
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- cerebras
- LLM
inference: false
base_model: cerebras/Cerebras-GPT-111M
---

# Instruction-tuned Cerebras GPT 111M

The smallest of [cerebras GPT models](https://huggingface.co/cerebras) with only 111M parameters instruction fine-tuned.

## Model Description

Instruction fine-tuned [cerebras-GPT-111M](https://huggingface.co/cerebras/Cerebras-GPT-111M)

## Evaluation

The model has been evaluated with Huggingface's Open LLM leaderboard. Have a look at the leaderboard for more details: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
The performance of the instruction fine-tuned model does improve compared to the cerebras base model by about 5.7% (average score):

Model                                          	| Average 	| ARC (25-shot) 	| HellaSwag (10-shot)  	| MMLU (5-shot)  	| TruthfulQA (0-shot)
--- | --- | --- | --- | --- | --- 
SebastianSchramm/Cerebras-GPT-111M-instruction 	| 31.6      	| 24.3            	| 26.2                  	| 26.5            	| 49.5                  	
cerebras/Cerebras-GPT-111M                     	| 29.9      	| 20              	| 26.7                  	| 26.7            	| 46.3                  	
||||||

## Training data

The model was fine-tuned with the following data: [alpaca_gpt4_data](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM/blob/main/data/alpaca_gpt4_data.json) (data generated by GPT-4 using Alpaca prompts for fine-tuning LLMs) and [alpaca_data_cleaned](https://github.com/tloen/alpaca-lora/blob/a3027fea37c2087b8b0131b21a4cd948bbdcd9e0/alpaca_data_cleaned.json).

## Prompt template

Fine-tuning was performed with the promp template from [stanford alpaca](https://github.com/tatsu-lab/stanford_alpaca):

```python
PROMPT_DICT = {
    "prompt_input": (
        "Below is an instruction that describes a task, paired with an input that provides further context. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
    ),
    "prompt_no_input": (
        "Below is an instruction that describes a task. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Response:"
    ),
}
```

## Usage

It is recommended to format input according to the prompt template mentioned above during inference for best results.