update

README.md

@@ -1,92 +1,45 @@
----
-library_name: transformers
-tags:
-- agriculture
-- question-answering
-- LoRA
-- tinyllama
-- fine-tuned
-- causal-lm
-license: apache-2.0
+# 🧠 AgriQA TinyLlama LoRA Adapter
+
+This repository contains a [LoRA](https://arxiv.org/abs/2106.09685) adapter fine-tuned on the [AgriQA](https://huggingface.co/datasets/shchoi83/agriQA) dataset using the [TinyLlama/TinyLlama-1.1B-Chat](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat) base model.
+
 ---
 
-# 🌾 AgriQA-TinyLlama-LoRA (Adapter)
+## 🔧 Model Details
 
-A **LoRA fine-tuned TinyLlama model** for answering agriculture-related questions in a conversational format. This adapter is fine-tuned on the [AgriQA dataset](https://huggingface.co/datasets/shchoi83/agriQA) using **parameter-efficient fine-tuning (PEFT)** and is suitable for low-resource inference scenarios.
+- **Base Model**: [`TinyLlama/TinyLlama-1.1B-Chat`](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat)
+- **Adapter Type**: LoRA (Low-Rank Adaptation)
+- **Adapter Size**: ~4.5MB
+- **Dataset**: [`shchoi83/agriQA`](https://huggingface.co/datasets/shchoi83/agriQA)
+- **Language**: English
+- **Task**: Instruction-tuned Question Answering in Agriculture domain
+- **Trained by**: [@theone049](https://huggingface.co/theone049)
 
-## 🧠 Model Details
+---
 
-- **Base Model:** [TinyLlama/TinyLlama-1.1B-Chat](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat)
-- **LoRA Adapter Size:** ~2MB
-- **Dataset:** [shchoi83/agriQA](https://huggingface.co/datasets/shchoi83/agriQA)
-- **Task:** Question Answering (Instruction Tuning)
-- **Language:** English
-- **Adapter Only:** This repository only contains the **LoRA adapter**. You must load it on top of the base model.
-- **Trained by:** [@theone049](https://huggingface.co/theone049)
+## 📌 Usage
 
-## 🚀 Usage
+To use this adapter, load it on top of the base model:
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel, PeftConfig
 
-# Load base model and tokenizer
+# Load base model
 base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat")
 tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat")
 
-# Load LoRA adapter
+# Load adapter
 model = PeftModel.from_pretrained(base_model, "theone049/agriqa-tinyllama-lora-adapter")
 
-# Inference
+# Run inference
 prompt = """### Instruction:
 Answer the agricultural question.
 
 ### Input:
-What is the control measure for aphid infestation in mustard crops?
+What is the ideal pH range for growing rice?
+
+### Response:"""
 
-### Response:
-"""
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=100)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
-
-## 📊 Training
-
-- **Epochs:** 3  
-- **Batch Size:** 8  
-- **Learning Rate:** 2e-5  
-- **Precision:** bf16  
-- **Training Framework:** 🤗 `transformers` + `peft`  
-- **Compute:** Google Colab T4 GPU
-
-## 📁 Files
-
-- `adapter_config.json`: Configuration of LoRA adapter.
-- `adapter_model.safetensors`: The trained adapter weights.
-- `README.md`: This file.
-
-## 🛑 Limitations
-
-- **Domain-Specific**: Works best on agri-related questions. Not suited for general conversation.
-- **Small Dataset**: Initial training was done on a subset (~5k samples). Accuracy may improve with full dataset.
-- **Not Merged**: Requires base model for usage.
-
-## 📚 Citation
-
-```bibtex
-@misc{nithyanandam2024agriqa,
-  title={AgriQA TinyLlama LoRA Adapter},
-  author={Nithyanandam Venu},
-  year={2024},
-  howpublished={\url{https://huggingface.co/theone049/agriqa-tinyllama-lora-adapter}}
-}
-```
-
-## ✉️ Contact
-
-For questions or collaborations: [[email protected]](mailto:[email protected])
-
----
-
-*This is part of an experimental project to improve AI Q&A for agriculture. Not for medical or pesticide advice.*