check windows on precommit

.github/workflows/causal_lm_cpp.yml

@@ -194,14 +194,18 @@ jobs:
         shell: cmd
         run: |
           call w_openvino_toolkit_windows_2024.1.0.15008.f4afc983258_x86_64\setupvars.bat
-
-          .\build\Release\beam_search_causal_lm.exe .\TinyLlama-1.1B-Chat-v1.0\ "69" > .\pred.txt
+          .\build\text_generation\causal_lm\cpp\Release\beam_search_causal_lm.exe .\TinyLlama-1.1B-Chat-v1.0\ "69" > .\pred.txt
+          echo "sample outputs"
+          type .\pred.txt
+          echo "huggingface outputs"
+          
           echo import transformers > ref.py
           echo predictions = open('pred.txt', 'r').read() >> ref.py
           echo tokenizer = transformers.LlamaTokenizer.from_pretrained('TinyLlama/TinyLlama-1.1B-Chat-v1.0') >> ref.py
           echo tokenized = tokenizer('69', return_tensors='pt') >> ref.py
           echo for beam in transformers.LlamaForCausalLM.from_pretrained('TinyLlama/TinyLlama-1.1B-Chat-v1.0').generate(**tokenized, num_beam_groups=3, num_beams=15, num_return_sequences=15, diversity_penalty=1.0, max_new_tokens=20, early_stopping=False, length_penalty=1.0, no_repeat_ngram_size=9**9, do_sample=False): >> ref.py
           echo     ref = ': ' + tokenizer.decode(beam[tokenized['input_ids'].numel():], skip_special_tokens=True) >> ref.py
+          echo     print(ref) >> ref.py
           echo     idx = predictions.find(ref) >> ref.py
           echo     if -1 == idx: >> ref.py
           echo         raise RuntimeError(f'Missing "{ref=}" from predictions') >> ref.py