Cropseek LLM

🚀 CropSeek-LLM

CropSeek-LLM is a fine - tuned language model. It offers insights and recommendations for crop optimization, addressing various agricultural practices such as crop planting, soil conditions, pest control, and irrigation.

🚀 Quick Start

Use the code below to start using the model:

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the fine-tuned model
model = AutoModelForCausalLM.from_pretrained("persadian/CropSeek-LLM", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("persadian/CropSeek-LLM")

# Example inference
input_text = "What is the best planting season for cabbages in South Coast, Durban?"
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

✨ Features

Model Details

CropSeek-LLM is a fine - tuned version of the deepseek - ai/DeepSeek - R1 - Distill - Qwen - 7B model. It uses LoRA (Low - Rank Adaptation) to fine - tune the base model on a crop - related Q&A dataset. It aims to assist farmers, agronomists, and researchers in crop management.

Uses

Direct Use

It can directly answer crop - optimization questions, including optimal planting seasons, ideal soil conditions, pest control methods, irrigation practices, and crop rotation strategies.

Downstream Use

It can be integrated into agricultural advisory systems, mobile apps, or chatbots to offer real - time recommendations.

Out - of - Scope Use

• Medical Advice: Not designed for medical or health - related advice.
• Financial Decisions: Should not be used for financial or investment decisions.
• Non - Agricultural Use: Specifically fine - tuned for crop optimization and may perform poorly in unrelated domains.

Bias, Risks, and Limitations

• Data Bias: Trained on a dataset focused on specific crops and regions, may not generalize well.
• Limited Scope: Designed for crop optimization, may not provide accurate answers for unrelated topics.
• Ethical Concerns: Should not replace professional advice from agronomists or experts.

⚠️ Important Note

The model has limitations. Users should verify its recommendations with local agricultural experts, be aware of its limitations, and report any biases or inaccuracies to the developers.

💡 Usage Tip

Use the model as a supplementary tool, not a replacement for professional advice.

Training Details

Training Data

The model was fine - tuned on a curated agricultural text dataset, including crop descriptions, disease symptoms and treatments, farming techniques, and regional guidelines. The specific dataset used is DARYJO/sawotiQ29_crop_optimization.

Training Procedure

Preprocessing

• Cleaned and preprocessed the dataset to remove irrelevant information and ensure consistency.
• Tokenized text data using the base - model's tokenizer.
• Applied data augmentation techniques like synonym replacement and paraphrasing.

Training Hyperparameters

• Training regime: Mixed precision (fp16)
• Batch size: 16
• Learning rate: 2e - 5
• Epochs: 3
• Optimizer: AdamW
• Weight decay: 0.01
• Warmup steps: 500

Speeds, Sizes, Times

• Training time: Approximately 10 hours on a T4 GPU.
• Checkpoint size: 1.5 GB
• Throughput: 120 samples/second

Evaluation

Testing Data, Factors & Metrics

Testing Data

Evaluated on a held - out test set of agricultural queries, including crop identification, disease diagnosis, and farming recommendations. [https://huggingface.co/datasets/DARJYO/sawotiQ29_crop_optimization]

Factors

Evaluation was disaggregated by crop type, disease type, and geographic region.

Metrics

• Accuracy: 92% on crop identification tasks.
• Precision/Recall/F1 - score: Precision: 0.89, Recall: 0.91, F1 - score: 0.90
• Latency: Average response time of 0.5 seconds on a T4 GPU.

Results

The model achieved high accuracy on crop identification and disease diagnosis tasks. Performance was slightly lower for region - specific recommendations due to limited training data.

Model Examination

Examined using interpretability tools like attention visualization and feature importance analysis. Key findings show that it relies on symptom descriptions for disease diagnosis and crop - specific keywords for crop identification.

Environmental Impact

• Hardware Type: T4 GPU
• Hours used: 10 hours
• Cloud Provider: Google Colab
• Compute Region: us - central1
• Carbon Emitted: Approximately 0.5 kg CO2eq

Technical Specifications

Model Architecture and Objective

• Base model architecture: deepseek - ai/deepseek - R1 - 14B
• Objective: Fine - tuned for text generation and classification tasks in the agricultural domain.

Compute Infrastructure

Hardware

• Training hardware: Google Colab with T4 GPU.

Software

• Frameworks: PyTorch, Hugging Face Transformers.
• Libraries: Datasets, Tokenizers, Accelerate.

Citation

BibTeX:

@misc{cropseek-llm,
  author = {persadian~Darshani Persadh, DARJYO},
  title = {CropSeek-LLM: A Fine-Tuned Language Model for Agricultural Applications},
  year = {2023},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/persadian/CropSeek-LLM}},
}

APA: persadian. Darshani Persadh (2023). CropSeek - LLM: A Fine - Tuned Language Model for Agricultural Applications. Hugging Face. https://huggingface.co/persadian/CropSeek - LLM

Glossary

• Mixed precision: Training using both 16 - bit and 32 - bit floating - point numbers to improve efficiency.

More Information

For more details, visit the CropSeek - LLM space on Hugging Face.

Model Card Authors

persadian ~Darshani Persah

Model Card Contact

info@darjyo.com