Update README.md

README.md

@@ -30,11 +30,11 @@ First make sure to `pip install -U transformers`, then copy the snippet from the
 
 ### Running on CPU
 
-```
+```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
+tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B")
+model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B")
 
 input_text = "שלום! מה שלומך היום?"
 input_ids = tokenizer(input_text, return_tensors="pt")
@@ -45,11 +45,11 @@ print(tokenizer.decode(outputs[0]))
 
 ### Running on GPU
 
-```
+```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B")
+model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B", device_map="auto")
 
 input_text = "שלום! מה שלומך היום?"
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -60,11 +60,11 @@ print(tokenizer.decode(outputs[0]))
 
 ### Running with 4-Bit precision
 
-```
+```python
 from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config = BitsAndBytesConfig(load_in_4bit=True))
+tokenizer = AutoTokenizer.from_pretrained("yam-peleg/Hebrew-Gemma-11B")
+model = AutoModelForCausalLM.from_pretrained("yam-peleg/Hebrew-Gemma-11B", quantization_config = BitsAndBytesConfig(load_in_4bit=True))
 
 input_text = "שלום! מה שלומך היום?"
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")