---
library_name: peft
base_model: mistralai/Mistral-7B-v0.1
license: apache-2.0
---

## Model Description

<!-- Provide a longer summary of what this model is. -->
The model is a fine-tuned (quantized) Mistral7b model on a self-organised dataset about environmental knowledge. This model is currently still under development. 


- **Developed by:** Fiona Zhang
- **Funded:** CSIRO, Pawsey Supercomputing Research Centre
- **Finetuned from model:** [Mistral7b](https://huggingface.co/mistralai/Mistral-7B-v0.1)

## 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. -->
This repository includes the weights learned during the training process. It should be loaded witht the pre-trained Mistral 7b and tokenizer.

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Load the tokenizer, adjust configuration if needed
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Load the fine-tuned model with its trained weights
fine_tuned_model = AutoModelForSequenceClassification.from_pretrained(
    'fionazhang/mistral_7b_environment',
)

# Now you can use `fine_tuned_model` for inference or further training
input_text = "The impact of climate change on"
output_text = fine_tuned_model.generate(tokenizer.encode(input_text, return_tensors="pt"))

print(tokenizer.decode(output_text[0], skip_special_tokens=True))

```


## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->
There are no modifications applied to the model. The model may return undesired or offensive response. Filters are encouraged to apply.


## Training Data

<!-- This should link to a Dataset 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. -->
The fine-tuning data are parsed from these public Wikipedia websites:
- [Environmental Issues](https://en.wikipedia.org/wiki/Environmental_issues)
- [Natural Environment](https://en.wikipedia.org/wiki/Natural_environment)
- [Biophysical Environment](https://en.wikipedia.org/wiki/Biophysical_environment)
- [Ecology](https://en.wikipedia.org/wiki/Ecology)
- [Environment (Systems)](https://en.wikipedia.org/wiki/Environment_(systems))
- [Built Environment](https://en.wikipedia.org/wiki/Built_environment)
- [Climate Change](https://en.wikipedia.org/wiki/Climate_change)
- [Human Impact on the Environment](https://en.wikipedia.org/wiki/Human_impact_on_the_environment)
- [Environment of Australia](https://en.wikipedia.org/wiki/Environment_of_Australia)
- [Environmental Protection](https://en.wikipedia.org/wiki/Environmental_protection)
- [Environmental Issues in Australia](https://en.wikipedia.org/wiki/Environmental_issues_in_Australia)

The text corpus are preprocessed for better format.

## Training Procedure 

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


## Training Hyperparameters

```python
training_arguments = TrainingArguments(
    output_dir="",
    num_train_epochs=1,
    per_device_train_batch_size=4,
    gradient_accumulation_steps=1,
    optim="paged_adamw_32bit",
    save_steps=25,
    logging_steps=25,
    learning_rate=2e-4,
    weight_decay=0.001,
    fp16=False,
    bf16=False,
    max_grad_norm=0.3,
    max_steps=-1,
    warmup_ratio=0.03,
    group_by_length=True,
    lr_scheduler_type="constant",
    report_to="wandb"
)
```


## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Not yet evaluated. Still working

## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

- **Hardware Type:** T4 GPU
- **Hours used:** <1
- **Cloud Provider:** Google Cloud
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

### Framework versions

- PEFT 0.7.1