N Neurarch Try it See it Changes Bot Pricing API Open app

Changes / Feeds / google/t5gemma-2b-2b-ul2-it

google/t5gemma-2b-2b-ul2-it

No tracked key changed across the 1 recorded revision since 2025-07-09. Head as last read: 6a196a58ce2786cd139a1217a85d1f7b9984e330.

Does vLLM send the reference prompt?

The chat template could not be rendered here, so whether vLLM sends the reference prompt is not known. Template at 6a196a58ce27, read 2026-11-17.

npx neurarch template-check google/t5gemma-2b-2b-ul2-it --engine vllm

Rendered with @huggingface/jinja from the template at that commit, the way vLLM hands it messages with --chat-template-content-format auto (the default): system, user and assistant content as text parts when the template reads parts, tool results as strings. That handling was measured end to end on 2026-11-13 through vLLM 0.33.0's own request parsing (parse_chat_messages) and transformers' apply_chat_template; it agreed with this page on all 18 models it could load; repositories that need custom code (InternVL, sarvam) could not be loaded there and are unconfirmed. SGLang, llama.cpp and other engines are not covered. same holds for a system+user turn, a multi-turn chat and a tool call, not every input.

Pin it, and let a bot move the pin

from_pretrained("google/t5gemma-2b-2b-ul2-it", revision="6a196a58ce2786cd139a1217a85d1f7b9984e330")

With the Renovate preset, a pull request moves this pin when the head moves, and links back here.

config changes badge

[![config changes](https://img.shields.io/endpoint?url=https%3A%2F%2Fwww.neurarch.com%2Fchanges-feeds%2Fbadge%2Fgoogle%2Ft5gemma-2b-2b-ul2-it.json)](https://www.neurarch.com/changes-feeds/models/google/t5gemma-2b-2b-ul2-it.html)