@@ -53,12 +53,12 @@ jobs:
53
53
wget https://huggingface.co/smangrul/tinyllama_lora_sql/resolve/main/adapter_model.safetensors?download=true -O adapter_model.safetensors
54
54
- run : >
55
55
. ./ov/setupvars.sh
56
- && timeout 35s ./build/samples/cpp/multinomial_causal_lm /multinomial_causal_lm ./open_llama_3b_v2/ a
56
+ && timeout 35s ./build/samples/cpp/text_generation /multinomial_causal_lm ./open_llama_3b_v2/ a
57
57
env:
58
58
PYTHONPATH: "./build"
59
59
- run : >
60
60
. ./ov/setupvars.sh
61
- && timeout 35s ./samples/python/multinomial_causal_lm /multinomial_causal_lm.py ./open_llama_3b_v2/ b
61
+ && timeout 35s ./samples/python/text_generation /multinomial_causal_lm.py ./open_llama_3b_v2/ b
62
62
env:
63
63
PYTHONPATH: "./build"
64
64
- run : >
78
78
matrix :
79
79
executable :
80
80
[
81
- ./build/samples/cpp/beam_search_causal_lm /beam_search_causal_lm,
82
- python ./samples/python/beam_search_causal_lm /beam_search_causal_lm.py,
81
+ ./build/samples/cpp/text_generation /beam_search_causal_lm,
82
+ python ./samples/python/text_generation /beam_search_causal_lm.py,
83
83
]
84
84
runs-on : ubuntu-20.04
85
85
defaults :
@@ -338,8 +338,8 @@ jobs:
338
338
optimum-cli export openvino --trust-remote-code --weight-format fp16 --model Qwen/Qwen1.5-7B-Chat Qwen1.5-7B-Chat
339
339
- run : >
340
340
. ./ov/setupvars.sh
341
- && timeout 50s ./build/samples/cpp/beam_search_causal_lm /beam_search_causal_lm ./Qwen1.5-7B-Chat/ "你好!"
342
- | diff <(timeout 50s ./samples/python/beam_search_causal_lm /beam_search_causal_lm.py ./Qwen1.5-7B-Chat/ "你好!") -
341
+ && timeout 50s ./build/samples/cpp/text_generation /beam_search_causal_lm ./Qwen1.5-7B-Chat/ "你好!"
342
+ | diff <(timeout 50s ./samples/python/text_generation /beam_search_causal_lm.py ./Qwen1.5-7B-Chat/ "你好!") -
343
343
env:
344
344
PYTHONPATH: "./build"
345
345
@@ -373,8 +373,8 @@ jobs:
373
373
optimum-cli export openvino --trust-remote-code --weight-format fp16 --model microsoft/phi-2 phi-2
374
374
- run : >
375
375
. ./ov/setupvars.sh
376
- && timeout 50s ./build/samples/cpp/beam_search_causal_lm /beam_search_causal_lm ./phi-2/ 69
377
- | diff <(timeout 50s ./samples/python/beam_search_causal_lm /beam_search_causal_lm.py ./phi-2/ 69) -
376
+ && timeout 50s ./build/samples/cpp/text_generation /beam_search_causal_lm ./phi-2/ 69
377
+ | diff <(timeout 50s ./samples/python/text_generation /beam_search_causal_lm.py ./phi-2/ 69) -
378
378
env:
379
379
PYTHONPATH: "./build"
380
380
@@ -408,8 +408,8 @@ jobs:
408
408
optimum-cli export openvino --trust-remote-code --weight-format fp16 --model argilla/notus-7b-v1 notus-7b-v1
409
409
- run : >
410
410
. ./ov/setupvars.sh
411
- && timeout 50s ./build/samples/cpp/beam_search_causal_lm /beam_search_causal_lm ./notus-7b-v1/ 69
412
- | diff <(timeout 50s ./samples/python/beam_search_causal_lm /beam_search_causal_lm.py ./notus-7b-v1/ 69) -
411
+ && timeout 50s ./build/samples/cpp/text_generation /beam_search_causal_lm ./notus-7b-v1/ 69
412
+ | diff <(timeout 50s ./samples/python/text_generation /beam_search_causal_lm.py ./notus-7b-v1/ 69) -
413
413
env:
414
414
PYTHONPATH: "./build"
415
415
@@ -445,9 +445,9 @@ jobs:
445
445
- name : run and compare
446
446
run : |
447
447
source ./ov/setupvars.sh
448
- ./build/samples/cpp/speculative_decoding_lm /speculative_decoding_lm ./dolly-v2-7b/ ./dolly-v2-3b/ "Alan Turing was a" > predictions_speculative.txt
448
+ ./build/samples/cpp/text_generation /speculative_decoding_lm ./dolly-v2-7b/ ./dolly-v2-3b/ "Alan Turing was a" > predictions_speculative.txt
449
449
./build/samples/cpp/text_generation/greedy_causal_lm ./dolly-v2-7b/ "Alan Turing was a" > predictions_greedy.txt
450
- python ./samples/python/speculative_decoding_lm /speculative_decoding_lm.py ./dolly-v2-7b/ ./dolly-v2-3b/ "Alan Turing was a" > predictions_py.txt
450
+ python ./samples/python/text_generation /speculative_decoding_lm.py ./dolly-v2-7b/ ./dolly-v2-3b/ "Alan Turing was a" > predictions_py.txt
451
451
python -c "
452
452
with open('predictions_greedy.txt', 'r') as f:
453
453
predicted_greedy = f.readline()
@@ -502,9 +502,9 @@ jobs:
502
502
Question: Can you please add 2 and 3
503
503
A:' > ./prompt.txt
504
504
505
- ./build/samples/cpp/prompt_lookup_decoding_lm /prompt_lookup_decoding_lm ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_prompt_lookup.txt
505
+ ./build/samples/cpp/text_generation /prompt_lookup_decoding_lm ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_prompt_lookup.txt
506
506
./build/samples/cpp/text_generation/greedy_causal_lm ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_greedy.txt
507
- python ./samples/python/prompt_lookup_decoding_lm /prompt_lookup_decoding_lm.py ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_py.txt
507
+ python ./samples/python/text_generation /prompt_lookup_decoding_lm.py ./TinyLlama-1.1B-Chat-v1.0/ "$(<prompt.txt)" > predictions_py.txt
508
508
python -c "
509
509
with open('predictions_greedy.txt', 'r') as f:
510
510
predicted_greedy = f.readline()
@@ -664,7 +664,7 @@ jobs:
664
664
run : |
665
665
source ./ov/setupvars.sh
666
666
printf 'What is 2 + 2?\nWhat is the previous answer?\nAdd 1 to it.\nSubtract 5 from it.\nWhy is the sun yellow?\nWhat was my first question?\n' > ./input.txt
667
- timeout 30s ./build/samples/cpp/chat_sample /chat_sample ./TinyLlama-1.1B-Chat-v1.0/ < input.txt > ./pred.txt
667
+ timeout 30s ./build/samples/cpp/text_generation /chat_sample ./TinyLlama-1.1B-Chat-v1.0/ < input.txt > ./pred.txt
668
668
python -c "
669
669
from transformers import AutoTokenizer, AutoModelForCausalLM
670
670
model_id = 'TinyLlama/TinyLlama-1.1B-Chat-v1.0'
@@ -693,7 +693,7 @@ jobs:
693
693
"
694
694
diff pred.txt ref.txt
695
695
echo "Chat sample cpp" passed
696
- timeout 30s ./samples/python/chat_sample /chat_sample.py ./TinyLlama-1.1B-Chat-v1.0/ < input.txt > ./pred2.txt
696
+ timeout 30s ./samples/python/text_generation /chat_sample.py ./TinyLlama-1.1B-Chat-v1.0/ < input.txt > ./pred2.txt
697
697
diff pred2.txt ref.txt
698
698
echo "Chat sample python" passed
699
699
0 commit comments