tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2025-12-06 04:12:13 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

revert change of base to sft for quick inline test

Browse Source
This commit is contained in:
Sofie Van Landeghem 2025-11-14 12:20:03 +01:00 committed by GitHub
parent b399e43168
commit c6f5bd67db
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
nanochat/engine.py
View File

@ -332,7 +332,7 @@ if __name__ == "__main__":
autocast_ctx = torch.amp.autocast(device_type=device_type, dtype=torch.bfloat16) if device_type == "cuda" else nullcontext() autocast_ctx = torch.amp.autocast(device_type=device_type, dtype=torch.bfloat16) if device_type == "cuda" else nullcontext()
# load the model and tokenizer # load the model and tokenizer
model, tokenizer, meta = load_model("sft", device, phase="eval") model, tokenizer, meta = load_model("base", device, phase="eval")
bos_token_id = tokenizer.get_bos_token_id() bos_token_id = tokenizer.get_bos_token_id()
# common hyperparameters # common hyperparameters
kwargs = dict(max_tokens=64, temperature=0.0) kwargs = dict(max_tokens=64, temperature=0.0)