zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-07-15 06:41:13 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

nits

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2025-02-22 02:12:02 +01:00
parent 235348c211
commit d653371e3d
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llms/mlx_lm/tuner/grpo_trainer.py
View File

@ -157,7 +157,6 @@ def generate_grpo(model: nn.Module, prompts, max_tokens, tokenizer, group_size,
current_input = expanded_prompts[idx] current_input = expanded_prompts[idx]
prompt_cache = cache.make_prompt_cache(model) prompt_cache = cache.make_prompt_cache(model)
# Initial forward pass with the prompt
logits = model(current_input[None], cache=prompt_cache)[:, -1] logits = model(current_input[None], cache=prompt_cache)[:, -1]
while len(current_tokens) < max_tokens: while len(current_tokens) < max_tokens: