AgroAdapt-Mixtral-8x7B

A PEFT (LoRA) fine-tuned Mixtral-8x7B-Instruct-v0.1 model for agricultural question answering, developed using the Adaption Labs AutoScientist workflow.

---

Overview

AgroAdapt-Mixtral-8x7B is a domain-adapted language model designed to improve agricultural instruction following and question answering. The model was fine-tuned using the Adaption Labs AutoScientist workflow on a curated agricultural instruction dataset covering practical farming knowledge.

Quick Facts

Item	Value
Domain	Agriculture
Task	Agricultural Question Answering
Base Model	Mixtral-8x7B-Instruct-v0.1
Fine-Tuning Method	PEFT (LoRA)
Training Framework	Adaption Labs AutoScientist
Language	English
Dataset	https://huggingface.co/datasets/Charley890/adaption-agricultural-qa-pairs
License	CC BY 4.0

Key Features

Agricultural Question Answering
Crop Production Guidance
Soil Science
Pest & Disease Identification
Irrigation Recommendations
Livestock Management
Climate-Smart Agriculture
Sustainable Farming
Agricultural Education

Base Model

Base Model: Mixtral-8x7B-Instruct-v0.1
Fine-tuning Method: PEFT (LoRA)
Training Framework: Adaption Labs AutoScientist
Language: English

Training Dataset

The model was trained using an adapted agricultural instruction dataset containing high-quality question-answer pairs covering:

Crop Production
Soil Science
Fertilizer Recommendations
Pest Management
Plant Disease Diagnosis
Irrigation
Livestock
Poultry
Sustainable Agriculture
Climate-Smart Agriculture
Farm Business
Agricultural Extension

Quick Start

The following example demonstrates how to load the LoRA adapter and perform inference using the Hugging Face Transformers ecosystem. The adapter is automatically merged with the base Mixtral model during inference.

Installation

pip install torch transformers peft accelerate

Load the Model

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

BASE_MODEL = "Mixtral-8x7B-Instruct-v0.1"
ADAPTER = "Charley890/AgroAdapt-Mixtral-8x7B"

tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)

model = AutoModelForCausalLM.from_pretrained(
    BASE_MODEL,
    device_map="auto",
    torch_dtype="auto"
)

model = PeftModel.from_pretrained(model, ADAPTER)

Inference

prompt = """
Farmer:
My tomato leaves are turning yellow with brown spots.
What could be the cause and how can I treat it?
"""

inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    temperature=0.7,
)

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

Expected Output

The model returns a practical, step-by-step agricultural recommendation based on the farmer's question, including possible causes, preventive measures, and treatment options.

Training Configuration

Parameter	Value
Fine-tuning Method	LoRA
Base Model	Mixtral-8x7B-Instruct
Epochs	5
LoRA Rank (r)	64
LoRA Alpha	128
Warmup Ratio	0.03
Optimizer	Cosine
Gradient Clipping	1.0
Target Modules	q_proj, k_proj, v_proj, o_proj

LoRA Equation

The adapter follows the standard LoRA formulation:

[ W' = W + \frac{\alpha}{r}BA ]

Where:

r = 64
α = 128

Scaling factor:

[ \frac{\alpha}{r} = \frac{128}{64} = 2 ]

This scaling improves learning efficiency while keeping the number of trainable parameters small.

Training Summary

Fine-tuned using Adaption Labs AutoScientist
5 training epochs
Win rate improved from 24% → 76%
Agriculture benchmark improved from 26% → 75%
Training loss decreased consistently throughout optimization.
Cosine learning-rate scheduling enabled smooth convergence.
Gradient clipping stabilized training and reduced optimization spikes.

Example

Input

How can I prevent maize leaf blight?

Output

Maize leaf blight can be reduced by planting resistant varieties, practicing crop rotation, avoiding overhead irrigation, removing infected crop residues, and applying recommended fungicides when disease pressure is high.

Evaluation Results

Evaluation performed using Adaption Labs AutoScientist

Metric	Base Model	Adapted Model	Improvement
Overall Win Rate	24%	76%	+52 pts
Agriculture Win Rate	26%	75%	+49 pts
Relative Improvement	—	—	216.7%
Agriculture Improvement	—	—	188.5%

Performance Summary

✓ Training Completed Successfully
✓ Stable Optimization
✓ Domain Adaptation Successful
✓ Agricultural Performance Improved
✓ Overall Win Rate Increased from 24% → 76%
✓ Agriculture Win Rate Increased from 26% → 75%

Evaluation Figures

Overall Training Win Rate

Agriculture Domain Win Rate

Evaluation Summary

Training Curves

Training Loss

Learning Rate

Gradient Norm

Interpretation

The fine-tuned model demonstrates a substantial improvement over the baseline model after domain adaptation using Adaption Labs AutoScientist. The evaluation shows a significant increase in both overall and agriculture-specific performance while maintaining stable optimization throughout training.

These results indicate that the model effectively learned agricultural reasoning and instruction-following capabilities from the domain-specific dataset.

Conclusion

Training Dynamics

Training Loss        ↘ steadily decreased
Validation Loss      → remained stable
Learning Rate        ↘ cosine decay schedule
Gradient Norm        → controlled through clipping
Adaptation Strategy  → LoRA parameter-efficient fine-tuning

Adaptive Optimization

while training:
    loss ↓
    learning_rate = cosine_decay(step)
    gradients = clip_norm(max_norm=1.0)
    weights = weights + LoRA_update()

Model Equation

Knowledge = Base Model + Domain Adaptation

M_adapted = M_base + LoRA(Agriculture)

Final Result

model: AgroAdapt-Mixtral-8x7B
framework: Adaption Labs AutoScientist
domain: Agriculture
training: Stable
convergence: Successful
adaptation: Optimized
status: Ready for Inference

AgroAdapt-Mixtral-8x7B successfully adapts the Mixtral foundation model into a specialized agricultural assistant through efficient LoRA fine-tuning, stable optimization, and domain-specific instruction learning, enabling practical, context-aware support for modern farming applications.

Intended Uses

This model is suitable for:

AI Farming Assistants
Agricultural Chatbots
Farm Advisory Systems
Agricultural Education
Agricultural Research
Smart Farming Applications
Decision Support Systems

Limitations

Although the model performs well on agricultural instruction tasks, responses should be verified before being used for real-world farming decisions. Local farming practices and expert guidance should always take precedence.

License

This model is released under the CC BY 4.0 License.

Acknowledgements

This project was developed as part of the Adaption Labs AutoScientist Challenge using the Mixtral-8x7B-Instruct-v0.1 base model.

Citation

If you use this model in your research or applications, please cite:

@misc{charlie2026agroadapt,
  title={AgroAdapt-Mixtral-8x7B},
  author={Edidiong Charlie},
  year={2026},
  publisher={Hugging Face},
  note={Adaption Labs AutoScientist Challenge}
}

Downloads last month: 227

Model tree for Charley890/AgroAdapt

Base model

mistralai/Mixtral-8x7B-v0.1

Finetuned

mistralai/Mixtral-8x7B-Instruct-v0.1

Adapter

(133)

this model