model: Add support for Tiny Aya Models (#19611)

* changes for tiny aya

* changes to hash

* changes to vocab

* fix some tokenizer regex edge cases

* update comment

* add some comments for regex

* Apply suggestion from @ngxson

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Saurabh Dash
2026-02-16 10:28:46 -05:00
committed by GitHub
parent 4408494144
commit 5f28c53d11
5 changed files with 36 additions and 2 deletions
+1
View File
@@ -99,6 +99,7 @@ models = [
{"name": "stablelm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b", },
{"name": "refact", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
{"name": "command-r", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
{"name": "tiny_aya", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereLabs/tiny-aya-base", },
{"name": "qwen2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
{"name": "dbrx", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },