Update README.md

README.md

@@ -77,17 +77,53 @@ Users should carefully evaluate outputs before deployment, especially in sensiti
 
 ## How to Get Started with the Model
 
+### Install dependencies
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+!pip install unsloth # @ git+https://github.com/unslothai/unsloth.git
+!pip install datasets==2.21.0
+!pip install pandas==2.1.4
+```
+
+### Import dependencies
+```python
+from unsloth import FastLanguageModel, is_bfloat16_supported
+from transformers import TextStreamer, AutoTokenizer
+import torch
+from datasets import load_dataset, DatasetDict, concatenate_datasets, Dataset
+from collections import Counter, defaultdict
+import os
+import sys
+
+from trl import SFTTrainer
+from transformers import TrainingArguments, TextStreamer
+import pandas as pd
+```
+
+### Load the base model
+```python
+model_config = {"model_name": "unsloth/llama-3-8b", "load_in_4bit": False}
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = False # Use 4bit quantization to reduce memory usage. Can be False.
+model_name = "polyglots/SinLlama_v01" # Change the model name
+```
 
-model_name = "polyglots/SinLlama_v01"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+### Load the model
+```python
+model, _ = FastLanguageModel.from_pretrained(
+    model_name = model_name,
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    resize_model_vocab=139336,
+    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+)
+```
 
-text = "සිංහල නවතම තාක්‍ෂණ විකාශනය පිළිබඳ පුවතක්"
-inputs = tokenizer(text, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=100)
-print(tokenizer.decode(outputs[0]))
+### Load our extended tokenizer
+```python
+tokenizer = AutoTokenizer.from_pretrained("polyglots/Extended-Sinhala-LLaMA")
+model.resize_token_embeddings(len(tokenizer))
 ```
 
 ## Training Details