Update README.md

README.md

@@ -38,13 +38,13 @@ dtype: bfloat16
 ## 💻 Usage
 
 ```python
-!pip install -qU transformers accelerate
+!pip install -qU transformers accelerate eniops
 
 from transformers import AutoTokenizer
 import transformers
 import torch
 
-model = "Isotonic/ohmistral-7b-ensemble"
+model = "Isotonic/ohmistral-7b-5.1"
 messages = [{"role": "user", "content": "What is a large language model?"}]
 
 tokenizer = AutoTokenizer.from_pretrained(model)
@@ -54,8 +54,9 @@ pipeline = transformers.pipeline(
     model=model,
     torch_dtype=torch.float16,
     device_map="auto",
+    trust_remote_code=True
 )
 
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.8, top_k=80, top_p=0.95)
 print(outputs[0]["generated_text"])
 ```