Describe Your Changes

This pull request updates various references to the tinyllama:gguf model to use the tinyllama:1b model instead. The changes span across multiple test files and configurations.

Model Reference Updates:

• docs/static/openapi/cortex.json: Updated the example model identifier from tinyllama:gguf to tinyllama:1b.

Test Files:

• engine/e2e-test/api/model/test_api_model.py: Replaced all occurrences of tinyllama:gguf with tinyllama:1b in the test_models_start_stop_should_be_successful method. [1] [2] [3]
• engine/e2e-test/api/model/test_api_model_import.py: Updated the model identifier in multiple test methods to tinyllama:1b. [1] [2]
• engine/e2e-test/cli/model/test_cli_model.py: Changed the model identifier to tinyllama:1b in CLI tests. [1] [2]
• engine/e2e-test/local_test.py: Modified the model identifier to tinyllama:1b in setup and teardown configurations. [1] [2] [3] [4]
• engine/e2e-test/test_api_docker.py: Updated the repo_branches list to include tinyllama:1b instead of tinyllama:gguf.
• engine/e2e-test/utils/test_runner.py: Changed the default model ID in the pull_model_if_needed function to tinyllama:1b.

C++ Test Files:

• engine/test/components/test_event.cc: Updated the model ID in the EventFromString test to tinyllama:1b.
• engine/test/components/test_huggingface_utils.cc: Modified the expected branches in the TestGetModelRepositoryBranches test to reflect the new model identifier tinyllama:1b.

Fixes Issues

• Closes #
• Closes #

Self Checklist

• Added relevant comments, esp in complex areas
• Updated docs (for bug fixes / features)
• Created issues for follow-up changes or refactoring needed