Update README.md

README.md

@@ -5,23 +5,20 @@ license: other
 license_name: llama3
 ---
 
-# Model Card for Model ID
-llama3-8b trained in 10k longest samples of OpenHermes
+# g-ronimo/llama3-8b-SlimHermes
+* `meta-llama/Meta-Llama-3-8B` trained on 10k of longest samples from `teknium/OpenHermes-2.5`
 
-## Usage
+## Sample Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 model_path = "g-ronimo/llama3-8b-SlimHermes"
-
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
-    # return_dict=True,
     torch_dtype=torch.bfloat16,
     device_map="auto",
 )
-
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 messages = [
@@ -40,6 +37,8 @@ output = tokenizer.decode(output_tokens[0], skip_special_tokens=False)
 print(output)
 ```
 
+## Sample Output
+
 ```
 <|im_start|>system
 Talk like a pirate.<|im_end|>