fionazhang/mistral_7b_environment

Model Description

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

Uses

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

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

There are no modifications applied to the model. The model may return undesired or offensive response. Filters are encouraged to apply.

Training Data

The fine-tuning data are parsed from these public Wikipedia websites:

• Environmental Issues
• Natural Environment
• Biophysical Environment
• Ecology
• Environment (Systems)
• Built Environment
• Climate Change
• Human Impact on the Environment
• Environment of Australia
• Environmental Protection
• Environmental Issues in Australia

The text corpus are preprocessed for better format.

Training Procedure

The fine-tuning is self-supervised.

Training Hyperparameters

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

Not yet evaluated. Still working

Environmental Impact

• 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