Update README.md

README.md

@@ -15,22 +15,26 @@ Women's health is a critical and often underserved topic, with limited accessibl
 
 ## Usage
 
-```
+```python
+
+max_seq_length = 2048
+dtype = None
+load_in_4bit = False
+lora_path = "altaidevorg/gemma-women-health-checkpoint-1292"
+use_streamer = False
+
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name=model_path,
+    lora_path,
     max_seq_length=max_seq_length,
     dtype=dtype,
     load_in_4bit=load_in_4bit,
 )
-FastLanguageModel.for_inference(model) 
+FastLanguageModel.for_inference(model)
 
 text_streamer = TextStreamer(tokenizer, skip_prompt = True)
 
-tokenizer = AutoTokenizer.from_pretrained('unsloth/gemma-2-2b-it')
-
 
 messages = [
-    #{"role": "system", "content": system_prompt},
     {"role": "user", "content": user_prompt},
 ]
 
@@ -44,7 +48,6 @@ input_ids = tokenizer.apply_chat_template(
 
 terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<end_of_turn>")]
 
-#input_ids = tokenizer(wiki, return_tensors="pt").input_ids.cuda()
 outputs = model.generate(input_ids = input_ids,
     streamer = text_streamer if use_streamer else None,
     max_new_tokens = 1024,
@@ -59,7 +62,6 @@ if not use_streamer:
 ```
 
 
-
 ## Dataset
 
 The dataset was prepared through a comprehensive process to ensure quality and relevance. Health-related websites were scraped, open-source e-books and PDFs focusing on women's health were collected, and an instruction dataset was created from these sources. To generate high-quality questions, we utilized the gemini-flash model, ensuring the dataset’s alignment with the domain.