Better formatting of hyperparams and code snippet (#19)

- Better formatting of hyperparams and code snippet (f6e92576a39bb842a2e1e3803ec9993d362a6c46)


Co-authored-by: Barbara Gendron <[email protected]>

README.md

@@ -11,6 +11,7 @@ License: mit
 ---
 hyperparams used to train this model:
 
+```
 lr = 5e-4,
 lr_schedule = constant, 
 wd=0.1,
@@ -18,17 +19,16 @@ adam_beta1=0.9, adam_beta2 = 0.95,
 context_length=512,
 batch_size=80,
 gradient_accumulation_steps=16
+```
 
 ------ EXAMPLE USAGE ---
 
+```py
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
 model = AutoModelForCausalLM.from_pretrained('roneneldan/TinyStories-33M')
-
 tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
-
 prompt = "Once upon a time there was"
-
 input_ids = tokenizer.encode(prompt, return_tensors="pt")
 
 # Generate completion
@@ -38,4 +38,5 @@ output = model.generate(input_ids, max_length = 1000, num_beams=1)
 output_text = tokenizer.decode(output[0], skip_special_tokens=True)
 
 # Print the generated text
-print(output_text)
+print(output_text)
+```