Update README.md

README.md

@@ -21,18 +21,17 @@ tags:
 ```python
 from unsloth import FastLanguageModel
 import torch
-max_seq_length = 4096 # Choose any! We auto support RoPE Scaling internally!
-dtype = torch.float16 # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
-load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+max_seq_length = 4096 
+dtype = torch.float16
+load_in_4bit = True
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "ArvindSharma18/Phi-3-mini-4k-instruct-bnb-4bit-Clinical-Trail-Merged", # "unsloth/mistral-7b" for 16bit loading
+    model_name = "ArvindSharma18/Phi-3-mini-4k-instruct-bnb-4bit-Clinical-Trail-Merged",
     max_seq_length = max_seq_length,
     dtype = dtype,
-    load_in_4bit = load_in_4bit,
-    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+    load_in_4bit = load_in_4bit
 )
-FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+FastLanguageModel.for_inference(model)
 inputs = tokenizer(
 [
     "Official Title: Randomized Trial of Usual Care vs. Specialized, Phase-specific Care for Youth at Risk for Psychosis"