Enable more supported models with ollama

[yanxi0830]

🚀 The feature, motivation and pitch

Context

• We currently have ollama supported models defined in

  llama-stack/llama_stack/providers/remote/inference/ollama/ollama.py

  Lines 42 to 69 in acbecbf

  	model_aliases = [
  	build_model_alias(
  	"llama3.1:8b-instruct-fp16",
  	CoreModelId.llama3_1_8b_instruct.value,
  	),
  	build_model_alias(
  	"llama3.1:70b-instruct-fp16",
  	CoreModelId.llama3_1_70b_instruct.value,
  	),
  	build_model_alias(
  	"llama3.2:1b-instruct-fp16",
  	CoreModelId.llama3_2_1b_instruct.value,
  	),
  	build_model_alias(
  	"llama3.2:3b-instruct-fp16",
  	CoreModelId.llama3_2_3b_instruct.value,
  	),
  	build_model_alias(
  	"llama-guard3:8b",
  	CoreModelId.llama_guard_3_8b.value,
  	),
  	build_model_alias(
  	"llama-guard3:1b",
  	CoreModelId.llama_guard_3_1b.value,
  	),
  	build_model_alias(
  	"x/llama3.2-vision:11b-instruct-fp16",
  	CoreModelId.llama3_2_11b_vision_instruct.value,

New Feature

• We should enable support for more llama models served with ollama, with updating these list of aliases.
• ollama supported llama models: https://ollama.com/search?q=llama

Alternatives

No response

Additional context

No response

[hickeyma]

@yanxi0830 I would like to work on this is that's OK?