Update README.md

README.md

@@ -4,7 +4,7 @@ tags: []
 widget:
 - messages:
   - role: user
-    content: How does the brain work?
+    content: Explain what monthly recurring revenue is.
 inference:
   parameters:
     max_new_tokens: 200
@@ -58,10 +58,10 @@ Below we share some code snippets on how to get quickly started with running the
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it")
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct")
 
-input_text = "Write me a poem about Machine Learning."
+input_text = "Explain what churn rate is."
 input_ids = tokenizer(input_text, return_tensors="pt")
 
 outputs = model.generate(**input_ids)
@@ -76,10 +76,10 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct", device_map="auto")
 
-input_text = "Write me a poem about Machine Learning."
+input_text = "How is click through rate calculated."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 
 outputs = model.generate(**input_ids)
@@ -95,10 +95,10 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct", device_map="auto", torch_dtype=torch.float16)
 
-input_text = "Write me a poem about Machine Learning."
+input_text = "What is an RFM analysis?"
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
 
 outputs = model.generate(**input_ids)
@@ -111,8 +111,8 @@ print(tokenizer.decode(outputs[0]))
 # pip install accelerate
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", device_map="auto", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct", device_map="auto", torch_dtype=torch.bfloat16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -131,8 +131,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -149,8 +149,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained("core-outline/gemma-2b-instruct")
+model = AutoModelForCausalLM.from_pretrained("core-outline/gemma-2b-instruct", quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")