zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-07-04 15:56:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2025-02-10 10:52:32 +01:00
parent 0dac286539
commit d9da35f458
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llms/mlx_lm/tuner/grpo_trainer.py
View File

@ -142,9 +142,6 @@ def generate_grpo(model, prompt, max_tokens, tokenizer, temperature):
if current_length >= end_sequence_length: if current_length >= end_sequence_length:
last_tokens = output[current_length - end_sequence_length:current_length].tolist() last_tokens = output[current_length - end_sequence_length:current_length].tolist()
# print(f"Last tokens: {last_tokens}")
# print(f"Decoded text: {tokenizer.decode(last_tokens)}")
# print(f"Target sequence: {end_sequence}")
if last_tokens == end_sequence: if last_tokens == end_sequence:
break break