You can deploy this model and start earning money today!

ElsayedGhonaim/
Agriculture_chatbot

Name: Agriculture_chatbot
Availability: InStock

safetensors

2309.16609

Views

No views yet

Of course. Here is the model card, regenerated with the information from the notebook you provided.

base_model: Qwen/Qwen1.5-1.8B-Chat library_name: peft pipeline_tag: text-generation tags:

base_model:adapter:Qwen/Qwen1.5-1.8B-Chat
lora
transformers

Model Card for ElsayedGhonaim/Agriculture_chatbot

This model is a fine-tuned version of Qwen/Qwen1.5-1.8B-Chat, specifically adapted for question-answering in the agricultural domain.

Model Details

Model Description

This is a causal language model fine-tuned using the Low-Rank Adaptation (LoRA) technique, which is a Parameter-Efficient Fine-Tuning (PEFT) method. The model is designed to act as a specialized chatbot or "agricultural assistant," providing answers to questions related to farming, crop management, soil health, and other agricultural topics.

Developed by: Elsayed Ghonaim
Shared by: Elsayed Ghonaim
Model type: Causal Language Model
Language(s) (NLP): English
License: Not specified
Finetuned from model: Qwen/Qwen1.5-1.8B-Chat

Model Sources

Repository: https://huggingface.co/ElsayedGhonaim/Agriculture_chatbot

Uses

Direct Use

The model is intended for direct use as a question-answering system for agricultural queries. It can be prompted in a conversational format.

python

# Example prompt
question = "How can I improve soil fertility naturally?"
# The model will generate a relevant answer.

Downstream Use

This model can be integrated into larger applications, such as:

Farming assistance applications for mobile devices.
Educational platforms for agriculture students.
Chatbot support for agricultural supply websites.

Out-of-Scope Use

This model is not a substitute for professional agronomic advice. It should not be used for making critical financial decisions or for diagnosing plant diseases with 100% certainty without expert consultation. The responses are generated based on patterns in the training data and may not always be accurate or up-to-date.

Bias, Risks, and Limitations

The model's knowledge is confined to the information present in its training dataset (KisanVaani/agriculture-qa-english-only). This may result in gaps in knowledge on niche or very recent agricultural topics. The dataset may contain inherent biases which could be reflected in the model's responses.

Recommendations

Users should be aware of the model's limitations and use its outputs as a starting point or a supplementary source of information. For critical applications, information should be verified by a qualified expert.

How to Get Started with the Model

Use the code below to load and run the model for inference.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the fine-tuned model and tokenizer
model = AutoModelForCausalLM.from_pretrained("ElsayedGhonaim/Agriculture_chatbot")
tokenizer = AutoTokenizer.from_pretrained("ElsayedGhonaim/Agriculture_chatbot")

# Move model to GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)

# Set the model to evaluation mode
model.eval()

def ask_question(question):
    # Format the input using the chat template
    messages = [
        {"role": "system", "content": "You are a helpful agricultural assistant."},
        {"role": "user", "content": question}
    ]
    
    # Apply the chat template
    prompt = tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
    )
    
    # Tokenize the input
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    
    # Generate response
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=256,
            temperature=0.7,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id,
            repetition_penalty=1.1
        )
    
    # Extract only the generated response
    response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    return response

# Example usage
question = "What are the benefits of drip irrigation for a small farm?"
answer = ask_question(question)
print(f"Question: {question}")
print(f"Answer: {answer}")

Training Details

Training Data

The model was fine-tuned on the KisanVaani/agriculture-qa-english-only dataset, which contains question-answer pairs related to agriculture.

Training Procedure

The model was fine-tuned for 3 epochs using the LoRA methodology.

Training Hyperparameters

Training regime: fp16 mixed precision
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
learning_rate: 2e-4
num_train_epochs: 3
per_device_train_batch_size: 1
gradient_accumulation_steps: 2
max_seq_length: 512

Citation

If you use this model, please consider citing the original Qwen base model.

BibTeX:

@misc{qwen,
      title={Qwen Technical Report}, 
      author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingxuan Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianing Zhang and Xingzhang Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
      year={2023},
      eprint={2309.16609},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Framework versions

PEFT 0.17.1
Transformers 4.55.4
Datasets 4.0.0
Accelerate 1.10.0
TRL 0.21.0
PyTorch 2.8.0+cu126
Bitsandbytes 0.47.0