Update Cerebras from Llama 3.1 to 3.3 (#645)

# What does this PR do?

Cerebras is rolling out support for llama 3.3 70b and deprecating llama
3.1 70b. This PR updates the documentation, config, and internal mapping
to reflect this change.

cc: @ashwinb @raghotham

docs/source/distributions/self_hosted_distro/cerebras.md

@@ -23,7 +23,7 @@ The following environment variables can be configured:
 The following models are available by default:
 
 - `meta-llama/Llama-3.1-8B-Instruct (llama3.1-8b)`
-- `meta-llama/Llama-3.1-70B-Instruct (llama3.1-70b)`
+- `meta-llama/Llama-3.3-70B-Instruct (llama-3.3-70b)`
 
 
 ### Prerequisite: API Keys

llama_stack/providers/remote/inference/cerebras/cerebras.py

@@ -41,8 +41,8 @@ model_aliases = [
         CoreModelId.llama3_1_8b_instruct.value,
     ),
     build_model_alias(
-        "llama3.1-70b",
-        CoreModelId.llama3_1_70b_instruct.value,
+        "llama-3.3-70b",
+        CoreModelId.llama3_3_70b_instruct.value,
     ),
 ]
 

llama_stack/templates/cerebras/run.yaml

@@ -56,9 +56,9 @@ models:
   provider_model_id: llama3.1-8b
   model_type: llm
 - metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
+  model_id: meta-llama/Llama-3.3-70B-Instruct
   provider_id: cerebras
-  provider_model_id: llama3.1-70b
+  provider_model_id: llama-3.3-70b
   model_type: llm
 - metadata:
     embedding_dimension: 384