initial

.gitattributes

@@ -0,0 +1 @@
+*.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,59 @@
+FROM ./unsloth.F16.gguf
+
+TEMPLATE """
+{{ if .Messages }}
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+{{- if .System }}
+
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+You are a helpful assistant specialized in providing information about plant diseases to Indian farmers. When you receive a tool call response, use the output to format an answer to the original user question.
+{{- end }}
+{{- end }}<|eot_id|>
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+{{- if and $.Tools $last }}
+
+Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+Respond in the format {"name": "function_name", "parameters": {"argument_name": "argument_value"}}. Do not use variables.
+
+{{ $.Tools }}
+{{- end }}
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+{{- if .ToolCalls }}
+
+{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+{{- else }}
+
+{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
+{{- end }}
+{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}
+"""
+PARAMETER stop "<|start_header_id|>"
+PARAMETER stop "<|end_header_id|>"
+PARAMETER stop "<|eot_id|>"
+PARAMETER stop "<|eom_id|>"
+PARAMETER temperature 1.5
+PARAMETER min_p 0.1

readme

@@ -0,0 +1,94 @@
+# AgriAssist-LLM: Plant Disease Information Assistant
+
+AgriAssist-LLM is a fine-tuned large language model based on Llama3.2:1B, specifically designed to provide detailed, actionable information about plant diseases to Indian farmers. It offers clear, concise, and locally relevant guidance on disease identification, symptoms, causes, severity, and treatment measures across major crops such as Sugarcane, Maize, Cotton, Rice, and Wheat.
+
+## Features
+
+- **Tailored Guidance:** Provides comprehensive details on various plant diseases affecting Indian crops.
+- **Practical Recommendations:** Offers clear instructions on treatment and prevention, helping farmers manage crop health.
+- **User-Friendly:** Utilizes the Alpaca Instruct Format to generate responses in simple, accessible language.
+- **Versatile Applications:** Suitable for use by farmers, agronomists, and agricultural extension workers.
+
+## Model Details
+
+- **Base Model:** Llama3.2:1B
+- **Fine-Tuning Dataset:** Custom dataset of 200 samples focusing on plant diseases in Indian agriculture.
+- **Intended Use:** Assisting in the identification, explanation, and management of plant diseases.
+
+## Installation
+
+To use AgriAssist-LLM, install the required libraries:
+
+```bash
+pip install transformers torch
+```
+
+## Usage
+
+### Using Hugging Face Transformers
+
+Here’s an example of how to use AgriAssist-LLM with the Hugging Face Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the tokenizer and model from the Hugging Face Hub
+tokenizer = AutoTokenizer.from_pretrained("your-username/AgriAssist-LLM")
+model = AutoModelForCausalLM.from_pretrained("your-username/AgriAssist-LLM")
+
+# Define a prompt
+prompt = "Explain Red Rot in sugarcane in simple terms for Indian farmers."
+
+# Tokenize and generate a response
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256)
+
+# Decode and print the generated response
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+*Note:* Replace `your-username/AgriAssist-LLM` with the actual path of your repository.
+
+### Using Ollama
+
+You can also use AgriAssist-LLM with [Ollama](https://ollama.ai), a simple way to run large language models locally.
+
+1. Install Ollama if you haven't already:
+
+```bash
+curl -fsSL https://ollama.ai/install.sh | sh
+```
+
+2. Pull the model from Hugging Face and convert it to an Ollama-compatible format.
+
+3. Run the model using Ollama:
+
+```bash
+ollama run AgriAssist-LLM "Explain Red Rot in sugarcane in simple terms for Indian farmers."
+```
+
+This will generate a response based on the model’s fine-tuned dataset.
+
+## Fine-Tuning and Training
+
+AgriAssist-LLM was fine-tuned using a custom dataset created in the Alpaca Instruct Format. The dataset covers detailed plant disease information tailored to the Indian context and includes samples for:
+
+- **Sugarcane:** Bacterial Blight, Healthy, Red Rot
+- **Maize:** Blight, Common Rust, Gray Leaf Spot, Healthy
+- **Cotton:** Bacterial Blight, Curl Virus, Fusarium Wilt, Healthy
+- **Rice:** Bacterial Blight, Blast, Brownspot, Tungro
+- **Wheat:** Healthy, Septoria, Strip Rust
+
+## Dataset
+
+The fine-tuning dataset consists of carefully curated samples that provide comprehensive, accurate information designed to help users manage crop diseases effectively.
+
+
+## Contact
+
+For questions or suggestions, please open an issue in the repository or contact the authors directly.
+
+---
+
+Happy farming with AgriAssist-LLM!
+

unsloth.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc600b570a00d3eacc8a51e1b6e4ec3737285e5ad116b548cd095cb9e3d8e09
+size 807694784