update transformer

README.md

@@ -36,7 +36,8 @@ Refer to the [original model card](https://huggingface.co/BioMistral/BioMistral-
 pip install mlx-lm
 ```
 
-The model was fine-tuned on [health_facts](https://huggingface.co/datasets/health_fact) and Synthetic EHR dataset inspired by MIMIC-IV, for 1000 steps using mlx
+The model was LoRA fine-tuned on [health_facts](https://huggingface.co/datasets/health_fact) and 
+Synthetic EHR dataset inspired by MIMIC-IV using the format below, for 1000 steps (~1M tokens) using mlx.
 
 ```python
 def format_prompt(prompt:str, question: str) -> str:
@@ -51,8 +52,8 @@ def format_prompt(prompt:str, question: str) -> str:
 
 Example For EHR Diagnosis
 ```
-Prompt = """You are an expert in provide diagnosis summary based on clinical notes.
-Objective: Your task is to generate concise summaries of the diagnosis, focusing on critical information"""
+Prompt = """You are an expert in provide diagnosis summary based on clinical notes inspired by MIMIC-IV-Note dataset.
+These notes encompass Chief Complaint along with Patient Summary & medical admission details."""
 ```
 
 Example for Healthfacts Check
@@ -60,7 +61,7 @@ Example for Healthfacts Check
 Prompt: You are a Public Health AI Assistant. You can do the fact-checking of public health claims. \nEach answer labelled with true, false, unproven or mixture. \nPlease provide the reason behind the answer
 ```
 
-## Model Loading Using mlx
+## Loading the model using `mlx`
 
 ```python
 from mlx_lm import generate, load
@@ -75,3 +76,25 @@ response = generate(
 )
 ```
 
+## Loading the model using `transformers`
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "abhishek-ch/biomistral-7b-synthetic-ehr"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForCausalLM.from_pretrained(repo_id)
+model.to("mps")
+
+input_text = format_prompt(system_prompt, question)
+input_ids = tokenizer(input_text, return_tensors="pt").to("mps")
+
+outputs = model.generate(
+    **input_ids,
+    max_new_tokens=512,
+)
+print(tokenizer.decode(outputs[0]))
+
+```
+