Description:

This is a llama 13b model merge of the LoRA with the same name.

Objective for this project:

To create a model that upholds a logical thread, regardless of whether the output is verbose or concise. Training has been performed on a version of the pile of sets, reduced to 40% of its original size, to expedite training iterations. I personally utilize this model as an aid for storytelling and writing. While it serves this purpose adequately, I still perceive this version as a prototype.

Prompt format:

Stanford Alpaca

The prompt should start on a new line after "### Response:"

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:
{instruction}

### Input:
{input}

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

### Instruction:
{instruction}

### Response:

Perplexity Benchmarks:

Training information:

Data used in training:

All cleaned and scrubbed in various ways then culled to various degrees.

Plans for the future, a brief overview:

Model used for training and other information:

https://huggingface.co/PocketDoc/llama-13b-gptq-4bit-128g

Merge model: https://huggingface.co/huggyllama/llama-13b

Disclaimer:

It has not been aligned and no warranty is given for the quality or safety of its outputs.