Llama2_Finetuned_SEO_Instruction_Set

Model Card for Model ID

Attempts to extract metadata; keywords, description and header count

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Israel N.
• Model type: Llama-2-7B
• Language(s) (NLP): English
• License: Apache-2.0
• Finetuned from model [optional]: TinyPixel/Llama-2-7B-bf16-sharded

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

Expediting offline SEO analysis

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

Currently does not respond to site or metadata, might need a more refined dataset to work.

How to Get Started with the Model

!pip install -q -U trl transformers accelerate git+https://github.com/huggingface/peft.git
!pip install -q datasets bitsandbytes einops

Import and use the AutoModelForCausalLM.pretrained to load the model from "israelNwokedi/Llama2_Finetuned_SEO_Instruction_Set".

Training Details

Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

Prompts: Entire sites and backlinks scrapped from the web Outputs: Keywords, description, header counts (h1-h6).

These are the main components of the dataset. Additional samples are ChatGPT-generated metadata as prompts and the relevant outputs.

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Finetuning of pre-trained "TinyPixel/Llama-2-7B-bf16-sharded" huggingface model using LoRA and QLoRA.

Preprocessing [optional]

Used Transformers' BitsAndBytesConfig for lightweight model training and "TinyPixel/Llama-2-7B-bf16-sharded" tokenizer for encoding/decoding.

Training Hyperparameters

• Training regime: 4-bit precision <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Data Card if possible. -->

Sampled from training data.

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

Not yet computed.

[More Information Needed]

Results

Intial test attempted reconstructing another artiicial metadata as part of its text generation function however this was not the intended usecase.

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> <!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). -->

• Hardware Type: Tesla T4
• Hours used: 0.5
• Cloud Provider: Google Colaboratory
• Compute Region: Eurpoe
• Carbon Emitted: 0.08