Add DeepSeek-R1-Distill-Qwen-14B as a supported model in tt-transformers

[jennychristopher]

Ticket

tenstorrent#25398

Problem description

TT-Transformers doesn't have support for DeepSeek-R1-Distill-Qwen-14B model

What's changed

Describe the approach used to solve the problem.
Summarize the changes made and its impact.

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.
• Galaxy quick CI passes (if applicable)
• TG demo tests, for Llama CI passes, if applicable, because of current Llama work
• (For runtime and ops writers) T3000 unit tests CI passes (if applicable, since this is run on push to main)
• (For models and ops writers) T3000 demo tests CI passes (if applicable, since this is required for release)
• (For models and ops writers) Single-card demo tests CI passes (if applicable, since this is required for release)
• New/Existing tests provide coverage for changes

[willwray]

This is good to go, thanks; I'll open a PR to TT, once a new conflict is resolved.

The conflict was highlighted in the web UI, blocking merge.
I tried the web UI conflict editor to fix the file-level conflicts, but it creates a merge commit that includes all changes to main.
I'll fixup manually, just the file, rebase then force push and open the PR.

[willwray]

I fixed the conflict and submitted the TT PR from a new branch

tenstorrent#26282