feat: Adds embed_tokens, lm_head as trainable for vocab expansion in peft and enables tying of adapters #625

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

dushyantbehl merged 12 commits into foundation-model-stack:main from romitjain:feat/embed-lmhead-tying-and-expansion

Nov 24, 2025

tests/artifacts/language_models/maykeye-tinyllama-v0/config.json

-Original file line number
+Diff line change
@@ Expand Up / @@ -14,7 +14,7 @@ @@
       "num_hidden_layers": 8,
       "pad_token_id": 0,
       "rms_norm_eps": 1e-06,
-      "tie_word_embeddings": false,
+      "tie_word_embeddings": true,
       "torch_dtype": "bfloat16",
       "transformers_version": "4.30.2",
       "use_cache": true,
@@ Expand Down @@