google/gemma-3-1b-it Bringup

[MohammedTaherMcW]

Ticket

Link to JIRA Issue

Problem description

Enabled Support for Gemma-3-1b-it Model.

What's changed

• Added support for gemma-3-1b-it model
• Updated model_config.py to support gemma-3-1b-it (BF16), including end-of-sequence (EoS) token handling and loading via Gemma3CausalLM.
• Updated load_checkpoints.py to support gemma-3-1b-it weight loading.
• Modified apply_scaling logic to handle both LLaMA and gemma-3-1b-it model.
• Added repetition penalty support in common.py.

Checklist

• All post commit CI passes
• Blackhole Post commit CI with demo tests passes (if applicable)
• Model regression CI passes (if applicable)
• Device performance regression CI passes (if applicable)
• (For models and ops writers) Single-card demo tests CI passes (if applicable) See recommended dev flow.
• New/Existing tests provide coverage for changes

[willwray]

For review, it is useful to know the origin of the files in the initial commit,
i.e. a link to the source in original form before any changes to port to TT.

E.g. the initial commit could be the original files (with a source link in the commit message)
then a second commit with the initial changes, so they are easy to see in diff view.