Update Cerebras examples to use Llama 3.3 70b (#17301)

docs/docs/examples/llm/cerebras.ipynb

@@ -103,7 +103,7 @@
     "    \"Enter your Cerebras API key: \"\n",
     ")\n",
     "\n",
-    "llm = Cerebras(model=\"llama3.1-70b\", api_key=os.environ[\"CEREBRAS_API_KEY\"])"
+    "llm = Cerebras(model=\"llama-3.3-70b\", api_key=os.environ[\"CEREBRAS_API_KEY\"])"
    ]
   },
   {

llama-index-integrations/llms/llama-index-llms-cerebras/README.md

@@ -44,7 +44,7 @@ import os
 from llama_index.core.llms import ChatMessage
 from llama_index.llms.cerebras import Cerebras
 
-llm = Cerebras(model="llama3.1-70b", api_key=os.environ["CEREBRAS_API_KEY"])
+llm = Cerebras(model="llama-3.3-70b", api_key=os.environ["CEREBRAS_API_KEY"])
 
 messages = [
     ChatMessage(
@@ -63,7 +63,7 @@ import os
 
 from llama_index.llms.cerebras import Cerebras
 
-llm = Cerebras(model="llama3.1-70b", api_key=os.environ["CEREBRAS_API_KEY"])
+llm = Cerebras(model="llama-3.3-70b", api_key=os.environ["CEREBRAS_API_KEY"])
 
 response = llm.stream_complete("What is Generative AI?")
 for r in response:

llama-index-integrations/llms/llama-index-llms-cerebras/llama_index/llms/cerebras/base.py

@@ -15,7 +15,7 @@ class Cerebras(OpenAILike):
         from llama_index.llms.cerebras import Cerebras
 
         # Set up the Cerebras class with the required model and API key
-        llm = Cerebras(model="llama3.1-70b", api_key="your_api_key")
+        llm = Cerebras(model="llama-3.3-70b", api_key="your_api_key")
 
         # Call the complete method with a query
         response = llm.complete("Why is fast inference important?")

llama-index-integrations/llms/llama-index-llms-cerebras/pyproject.toml

@@ -30,7 +30,7 @@ license = "MIT"
 name = "llama-index-llms-cerebras"
 packages = [{include = "llama_index/"}]
 readme = "README.md"
-version = "0.2.1"
+version = "0.2.2"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"