Update README.md

README.md

@@ -6,25 +6,34 @@ license: mit
 
 This model is a mixture of experts merge consisting of 3 mistral based models
 
-base model,- **openchat/openchat-3.5-0106**
+base model, **openchat/openchat-3.5-0106**
 
-code expert,- **beowolx/CodeNinja-1.0-OpenChat-7B**
+code expert, **beowolx/CodeNinja-1.0-OpenChat-7B**
 
-math expert,- **meta-math/MetaMath-Mistral-7B**
+math expert, **meta-math/MetaMath-Mistral-7B**
 
 ### Usage
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "Chickaboo/Chicka-Mistral-4x7b"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+device = "cuda" # the device to load the model onto
 
-model = AutoModelForCausalLM.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
 
-text = "Hello my name is"
-inputs = tokenizer(text, return_tensors="pt")
+messages = [
+    {"role": "user", "content": "What is your favourite condiment?"},
+    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
+    {"role": "user", "content": "Do you have mayonnaise recipes?"}
+]
 
-outputs = model.generate(**inputs, max_new_tokens=20)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+
+model_inputs = encodeds.to(device)
+model.to(device)
+
+generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+decoded = tokenizer.batch_decode(generated_ids)
+print(decoded[0])
 ```