openvinotoolkit · yatarkan · Oct 27, 2025 · Oct 27, 2025 · Oct 27, 2025 · Oct 27, 2025
diff --git a/tests/python_tests/data/models.py b/tests/python_tests/data/models.py
@@ -8,7 +8,7 @@
 
 def get_models_list():
     model_ids = [
-        "katuni4ka/tiny-random-phi3",
+        "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM",
     ]
     if pytest.selected_model_ids:
         model_ids = [model_id for model_id in model_ids if model_id in pytest.selected_model_ids.split(' ')]

diff --git a/tests/python_tests/data/tokenizer_configs.py b/tests/python_tests/data/tokenizer_configs.py
@@ -670,7 +670,7 @@ def get_tokenizer_configs():
             "unk_token": "<unk>",
             "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>'+ '\n' + message['content'] + '\n'}}{% elif message['role'] == 'user' %}{{'<|user|>' + '\n' + message['content'] + '\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>' + '\n' + message['content'] + '<|endoftext|>' + ('' if loop.last else '\n')}}{% endif %}{% endfor %}"
         },
-        "katuni4ka/tiny-random-phi3": {
+        "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM": {
             "bos_token": "<s>",
             "eos_token": "<|endoftext|>",
             "pad_token": "<|endoftext|>",
@@ -712,7 +712,7 @@ def get_tokenizer_configs():
             "unk_token": "<unk>",
             "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### User:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### System:\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant:\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:' }}\n{% endif %}\n{% endfor %}"
         },
-        "katuni4ka/tiny-random-minicpm": {
+        "optimum-intel-internal-testing/tiny-random-minicpm": {
             "bos_token": "<s>",
             "eos_token": "</s>",
             "pad_token": None,

diff --git a/tests/python_tests/samples/conftest.py b/tests/python_tests/samples/conftest.py
@@ -97,7 +97,7 @@
         "convert_args": []
     },
     "tiny-random-minicpmv-2_6": {
-        "name": "katuni4ka/tiny-random-minicpmv-2_6",
+        "name": "optimum-intel-internal-testing/tiny-random-minicpmv-2_6",
         "convert_args": ['--trust-remote-code', "--task", "image-text-to-text"]
     },
     "InternVL2-1B": {
@@ -121,15 +121,15 @@
         "convert_args": ["--task", "text-generation-with-past", "--weight-format", "int8"]
     },
     "tiny-random-latent-consistency": {
-        "name": "echarlaix/tiny-random-latent-consistency",
+        "name": "optimum-intel-internal-testing/tiny-random-latent-consistency",
         "convert_args": ['--trust-remote-code', '--weight-format', 'fp16']
     },
     "tiny-random-latent-consistency-lora": {
         "name": "katuni4ka/tiny-random-latent-consistency-lora",
         "convert_args": []
     },
     "tiny-random-llava": {
-        "name": "katuni4ka/tiny-random-llava",
+        "name": "optimum-intel-internal-testing/tiny-random-llava",
         "convert_args": ["--trust-remote-code", "--task", "image-text-to-text"]
     },
     "bge-small-en-v1.5": {

diff --git a/tests/python_tests/test_llm_pipeline.py b/tests/python_tests/test_llm_pipeline.py
@@ -99,7 +99,7 @@ def test_batch_string_inputs(model_id, generation_config_dict, prompts, pipeline
 
 @pytest.mark.precommit
 def test_batch_size_switch():
-    model_id = 'katuni4ka/tiny-random-phi3'
+    model_id = 'optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM'
     _, _, models_path = download_and_convert_model(model_id)
     ov_pipe = create_ov_pipeline(models_path)
 
@@ -110,7 +110,7 @@ def test_batch_size_switch():
 
 @pytest.mark.precommit
 def test_empty_encoded_inputs_throw():
-    model_id = 'katuni4ka/tiny-random-phi3'
+    model_id = 'optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM'
     _, _, models_path = download_and_convert_model(model_id)
     ov_pipe = create_ov_pipeline(models_path)
 
@@ -696,7 +696,7 @@ def run_perf_metrics_collection(model_id, generation_config_dict: dict, prompt:
 def test_perf_metrics(generation_config, prompt):
     import time
     start_time = time.perf_counter()
-    model_id = 'katuni4ka/tiny-random-gemma2'
+    model_id = 'optimum-intel-internal-testing/tiny-random-gemma2'
     perf_metrics = run_perf_metrics_collection(model_id, generation_config, prompt)
     total_time = (time.perf_counter() - start_time) * 1000
 
@@ -778,7 +778,7 @@ class Person(BaseModel):
         city: Literal["Dublin", "Dubai", "Munich"]
     generation_config.update(dict(structured_output_config=ov_genai.StructuredOutputConfig(json_schema=json.dumps(Person.model_json_schema()))))
 
-    model_id = 'katuni4ka/tiny-random-gemma2'
+    model_id = 'optimum-intel-internal-testing/tiny-random-gemma2'
     _, _, models_path = download_and_convert_model(model_id)
     ov_pipe = create_ov_pipeline(models_path)
     perf_metrics = ov_pipe.generate([prompt], **generation_config).perf_metrics

diff --git a/tests/python_tests/test_sampling.py b/tests/python_tests/test_sampling.py
@@ -29,7 +29,7 @@
                             #   "echo_with_generation",
                               ])
 def test_basic_stop_criteria(generation_config, prompt):
-    model_id : str = "katuni4ka/tiny-random-phi3"
+    model_id : str = "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM"
     generate_and_compare(model_id, [prompt], generation_config)
 
 
@@ -71,7 +71,7 @@ def test_stop_strings(generation_config, model_id, pipeline_type):
     'I have an interview about product speccing with the company Weekend Health. Give me an example of a question they might ask with regards about a new feature'
 ])
 def test_greedy(generation_config, prompt):
-    model_id : str = "katuni4ka/tiny-random-phi3"
+    model_id : str = "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM"
     prompt = prompt.decode('unicode_escape') if isinstance(prompt, bytes) else prompt
 
     generate_and_compare(model=model_id, 

diff --git a/tests/python_tests/test_stateful_speculative_decoding.py b/tests/python_tests/test_stateful_speculative_decoding.py
@@ -71,7 +71,7 @@ def test_string_inputs(main_model, main_device, draft_model, draft_device, promp
 def test_perf_metrics():
     import time
     start_time = time.perf_counter()
-    model_id = 'katuni4ka/tiny-random-gemma2'
+    model_id = 'optimum-intel-internal-testing/tiny-random-gemma2'
     _, _, model_path = download_and_convert_model(model_id)
 
     # Create OpenVINO GenAI pipeline:

diff --git a/tests/python_tests/test_structured_output.py b/tests/python_tests/test_structured_output.py
@@ -35,7 +35,7 @@ class RESTAPIResponse(BaseModel):
 
 structured_id_models = [
     "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-    "katuni4ka/tiny-random-phi3",
+    "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM",
 ]
 
 

diff --git a/tests/python_tests/test_tokenizer.py b/tests/python_tests/test_tokenizer.py
@@ -308,7 +308,7 @@ def test_set_chat_template(ov_hf_tokenizers):
 @pytest.mark.parametrize(
     "ov_hf_tokenizers",
     [
-        "katuni4ka/tiny-random-phi3",
+        "optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM",
         "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
         # ("black-forest-labs/FLUX.1-dev", dict(subfolder="tokenizer")),  # FLUX.1-dev has tokenizer in subfolder
     ],
@@ -420,10 +420,10 @@ def hf_ov_genai_models(request, tmp_path_factory):
 @pytest.mark.parametrize(
     "hf_ov_genai_models",
     [
-        ("katuni4ka/tiny-random-phi3", {"padding_side": None}),
+        ("optimum-intel-internal-testing/tiny-random-Phi3ForCausalLM", {"padding_side": None}),
         ("TinyLlama/TinyLlama-1.1B-Chat-v1.0", {"padding_side": None}),
-        ("katuni4ka/tiny-random-llava-next", {"padding_side": "right"}),
-        ("katuni4ka/tiny-random-llava-next", {"padding_side": "left"}),
+        ("optimum-intel-internal-testing/tiny-random-llava-next", {"padding_side": "right"}),
+        ("optimum-intel-internal-testing/tiny-random-llava-next", {"padding_side": "left"}),
         (
             "BAAI/bge-small-en-v1.5",
             {"padding_side": None},
@@ -485,8 +485,8 @@ def test_padding(
 base_models_for_paired_input_test = [
     ("answerdotai/ModernBERT-base", {"padding_side": None}),
     ("TinyLlama/TinyLlama-1.1B-Chat-v1.0", {"padding_side": None}),
-    ("katuni4ka/tiny-random-llava-next", {"padding_side": "right"}),
-    ("katuni4ka/tiny-random-llava-next", {"padding_side": "left"}),
+    ("optimum-intel-internal-testing/tiny-random-llava-next", {"padding_side": "right"}),
+    ("optimum-intel-internal-testing/tiny-random-llava-next", {"padding_side": "left"}),
 ]
 
 def make_model_params():

diff --git a/tests/python_tests/test_vlm_pipeline.py b/tests/python_tests/test_vlm_pipeline.py
@@ -80,20 +80,20 @@ class VlmModelInfo:
 
 
 VIDEO_MODEL_IDS = [
-    "katuni4ka/tiny-random-llava-next-video",
+    "optimum-intel-internal-testing/tiny-random-llava-next-video",
 ]
 
 
 MODEL_IDS: list[str] = [
-    "katuni4ka/tiny-random-minicpmv-2_6",
-    "katuni4ka/tiny-random-phi3-vision",
-    "katuni4ka/tiny-random-phi-4-multimodal",
-    "katuni4ka/tiny-random-llava",
-    "katuni4ka/tiny-random-llava-next",
-    "katuni4ka/tiny-random-internvl2",
-    "katuni4ka/tiny-random-qwen2vl",
-    "katuni4ka/tiny-random-qwen2.5-vl",
-    "katuni4ka/tiny-random-gemma3",
+    "optimum-intel-internal-testing/tiny-random-minicpmv-2_6",
+    "optimum-intel-internal-testing/tiny-random-phi3-vision",
+    "optimum-intel-internal-testing/tiny-random-phi-4-multimodal",
+    "optimum-intel-internal-testing/tiny-random-llava",
+    "optimum-intel-internal-testing/tiny-random-llava-next",
+    "optimum-intel-internal-testing/tiny-random-internvl2",
+    "optimum-intel-internal-testing/tiny-random-qwen2vl",
+    "optimum-intel-internal-testing/tiny-random-qwen2.5-vl",
+    "optimum-intel-internal-testing/tiny-random-gemma3",
     "qnguyen3/nanoLLaVA",
     *VIDEO_MODEL_IDS,
 ]
@@ -106,28 +106,28 @@ class VlmModelInfo:
 
 
 TAG_GENERATOR_BY_MODEL: dict[str, Callable[[int], str]] = {
-    "katuni4ka/tiny-random-llava": lambda idx: "<image>",
-    "katuni4ka/tiny-random-llava-next": lambda idx: "<image>",
-    "katuni4ka/tiny-random-qwen2vl": lambda idx: "<|vision_start|><|image_pad|><|vision_end|>",
-    "katuni4ka/tiny-random-qwen2.5-vl": lambda idx: "<|vision_start|><|image_pad|><|vision_end|>",
-    "katuni4ka/tiny-random-gemma3": lambda idx: "<start_of_image>",
-    "katuni4ka/tiny-random-internvl2": lambda idx: "<image>\n",
-    "katuni4ka/tiny-random-minicpmv-2_6": lambda idx: "<image>./</image>\n",
-    "katuni4ka/tiny-random-phi3-vision": lambda idx: f"<|image_{idx + 1}|>\n",
-    "katuni4ka/tiny-random-llava-next-video": lambda idx: "<image>\n",
+    "optimum-intel-internal-testing/tiny-random-llava": lambda idx: "<image>",
+    "optimum-intel-internal-testing/tiny-random-llava-next": lambda idx: "<image>",
+    "optimum-intel-internal-testing/tiny-random-qwen2vl": lambda idx: "<|vision_start|><|image_pad|><|vision_end|>",
+    "optimum-intel-internal-testing/tiny-random-qwen2.5-vl": lambda idx: "<|vision_start|><|image_pad|><|vision_end|>",
+    "optimum-intel-internal-testing/tiny-random-gemma3": lambda idx: "<start_of_image>",
+    "optimum-intel-internal-testing/tiny-random-internvl2": lambda idx: "<image>\n",
+    "optimum-intel-internal-testing/tiny-random-minicpmv-2_6": lambda idx: "<image>./</image>\n",
+    "optimum-intel-internal-testing/tiny-random-phi3-vision": lambda idx: f"<|image_{idx + 1}|>\n",
+    "optimum-intel-internal-testing/tiny-random-llava-next-video": lambda idx: "<image>\n",
     "qnguyen3/nanoLLaVA": lambda idx: "<image>\n",
 }
 
 
 RESOLUTION_BY_MODEL: dict[str, int | None] = {
-    "katuni4ka/tiny-random-gemma3": 32,
+    "optimum-intel-internal-testing/tiny-random-gemma3": 32,
     "qnguyen3/nanoLLaVA": 384,
-    "katuni4ka/tiny-random-llava-next-video": 336,
+    "optimum-intel-internal-testing/tiny-random-llava-next-video": 336,
 }
 
 
 RESOLUTION_BY_VIDEO_MODEL: dict[str, int | None] = {
-    "katuni4ka/tiny-random-llava-next-video": 32,
+    "optimum-intel-internal-testing/tiny-random-llava-next-video": 32,
 }
 
 
@@ -152,8 +152,8 @@ class VlmModelInfo:
 
 
 NPU_UNSUPPORTED_MODELS = {
-    "katuni4ka/tiny-random-internvl2",
-    "katuni4ka/tiny-random-gemma3",
+    "optimum-intel-internal-testing/tiny-random-internvl2",
+    "optimum-intel-internal-testing/tiny-random-gemma3",
 }
 
 
@@ -178,9 +178,9 @@ def _setup_generation_config(
 
 
 def _get_ov_model(model_id: str) -> str:
-    if model_id in {"katuni4ka/tiny-random-phi-4-multimodal", "qnguyen3/nanoLLaVA"}:
+    if model_id in {"optimum-intel-internal-testing/tiny-random-phi-4-multimodal", "qnguyen3/nanoLLaVA"}:
         pytest.skip("ValueError: The current version of Transformers does not allow for the export of the model. Maximum required is 4.53.3, got: 4.55.4")
-    if "katuni4ka/tiny-random-phi3-vision" == model_id:
+    if "optimum-intel-internal-testing/tiny-random-phi3-vision" == model_id:
         pytest.xfail("AttributeError: 'DynamicCache' object has no attribute 'get_usable_length'. Ticket CVS-175110")
     ov_cache_models_dir = get_ov_cache_models_dir()
     dir_name = str(model_id).replace(os.sep, "_")
@@ -203,10 +203,10 @@ def _get_ov_model(model_id: str) -> str:
             export=True,
             load_in_8bit=False,
             trust_remote_code=model_id in {
-                "katuni4ka/tiny-random-minicpmv-2_6",
-                "katuni4ka/tiny-random-internvl2",
-                "katuni4ka/tiny-random-phi3-vision",
-                "katuni4ka/tiny-random-phi-4-multimodal",
+                "optimum-intel-internal-testing/tiny-random-minicpmv-2_6",
+                "optimum-intel-internal-testing/tiny-random-internvl2",
+                "optimum-intel-internal-testing/tiny-random-phi3-vision",
+                "optimum-intel-internal-testing/tiny-random-phi-4-multimodal",
                 "qnguyen3/nanoLLaVA",
             },
         )
@@ -809,7 +809,7 @@ def test_perf_metrics(
     max_new_tokens = DEFAULT_MAX_NEW_TOKENS
 
     # Using non-cached model to get more accurate load time
-    model_path = _get_ov_model("katuni4ka/tiny-random-minicpmv-2_6")
+    model_path = _get_ov_model("optimum-intel-internal-testing/tiny-random-minicpmv-2_6")
     start_time = perf_counter_ns()
     pipe = VLMPipeline(model_path, "CPU", ATTENTION_BACKEND=backend)
     start_generate = perf_counter_ns()
@@ -1147,24 +1147,24 @@ def conversation_requests(
 
 
 TAG_INSERTED_BY_TEMPLATE = [
-    ("katuni4ka/tiny-random-llava", "PA"),
-    ("katuni4ka/tiny-random-llava-next", "PA"),
-    ("katuni4ka/tiny-random-qwen2vl", "PA"),
-    ("katuni4ka/tiny-random-qwen2.5-vl", "PA"),
-    ("katuni4ka/tiny-random-gemma3", "SDPA"),
+    ("optimum-intel-internal-testing/tiny-random-llava", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-llava-next", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-qwen2vl", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-qwen2.5-vl", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-gemma3", "SDPA"),
     ("qnguyen3/nanoLLaVA", "PA"),
-    ("katuni4ka/tiny-random-llava-next-video", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-llava-next-video", "PA"),
 ]
 
 
 IMAGE_ID_IGNORANT_MODELS_TO_TAG = TAG_INSERTED_BY_TEMPLATE + [
-    ("katuni4ka/tiny-random-internvl2", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-internvl2", "PA"),
 ]
 
 
 MODELS_TO_TAG = IMAGE_ID_IGNORANT_MODELS_TO_TAG + [
-    ("katuni4ka/tiny-random-minicpmv-2_6", "PA"),
-    ("katuni4ka/tiny-random-phi3-vision", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-minicpmv-2_6", "PA"),
+    ("optimum-intel-internal-testing/tiny-random-phi3-vision", "PA"),
 ]
 
 
@@ -1395,20 +1395,20 @@ def test_model_tags_missing_native(ov_pipe_model: VlmModelInfo):
 @pytest.mark.parametrize(
     "ov_pipe_model",
     [
-        pytest.param(("katuni4ka/tiny-random-qwen2vl","SDPA")),
-        pytest.param(("katuni4ka/tiny-random-qwen2vl", "PA")),
-        pytest.param(("katuni4ka/tiny-random-qwen2.5-vl", "SDPA")),
-        pytest.param(("katuni4ka/tiny-random-qwen2.5-vl", "PA"), marks=pytest.mark.xfail(reason="CVS-167316")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-qwen2vl","SDPA")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-qwen2vl", "PA")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-qwen2.5-vl", "SDPA")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-qwen2.5-vl", "PA"), marks=pytest.mark.xfail(reason="CVS-167316")),
         (
-            pytest.param(("katuni4ka/tiny-random-gemma3", "SDPA"), marks=pytest.mark.xfail(reason=GEMMA3_MACOS_XFAIL_REASON)) 
+            pytest.param(("optimum-intel-internal-testing/tiny-random-gemma3", "SDPA"), marks=pytest.mark.xfail(reason=GEMMA3_MACOS_XFAIL_REASON)) 
             if sys.platform == "darwin" 
-            else pytest.param(("katuni4ka/tiny-random-gemma3",  "SDPA"))
+            else pytest.param(("optimum-intel-internal-testing/tiny-random-gemma3",  "SDPA"))
         ),
-        pytest.param(("katuni4ka/tiny-random-gemma3", "PA"), marks=pytest.mark.xfail(reason="CVS-171180")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-gemma3", "PA"), marks=pytest.mark.xfail(reason="CVS-171180")),
         pytest.param(("qnguyen3/nanoLLaVA", "SDPA")),
         pytest.param(("qnguyen3/nanoLLaVA", "PA")),
-        pytest.param(("katuni4ka/tiny-random-llava-next-video", "SDPA")),
-        pytest.param(("katuni4ka/tiny-random-llava-next-video", "PA")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-llava-next-video", "SDPA")),
+        pytest.param(("optimum-intel-internal-testing/tiny-random-llava-next-video", "PA")),
     ],
     ids=lambda p: f"{p[0]}/{p[1]}",
     indirect=["ov_pipe_model"],

diff --git a/tools/who_what_benchmark/tests/test_cli_image.py b/tools/who_what_benchmark/tests/test_cli_image.py
@@ -13,10 +13,10 @@
 logger = logging.getLogger(__name__)
 
 MODEL_CACHE = tempfile.mkdtemp()
-OV_IMAGE_MODELS = ["echarlaix/tiny-random-stable-diffusion-xl",
-                   "yujiepan/stable-diffusion-3-tiny-random",
-                   "katuni4ka/tiny-random-flux",
-                   "katuni4ka/tiny-random-flux-fill"]
+OV_IMAGE_MODELS = ["optimum-intel-internal-testing/tiny-random-stable-diffusion-xl",
+                   "optimum-intel-internal-testing/stable-diffusion-3-tiny-random",
+                   "optimum-intel-internal-testing/tiny-random-flux",
+                   "optimum-intel-internal-testing/tiny-random-flux-fill"]
 
 
 def run_wwb(args):
@@ -111,7 +111,7 @@ def test_image_model_genai(model_id, model_type, tmp_path):
         pytest.skip(reason="FLUX-Fill is supported as inpainting only")
     if model_type == "image-inpainting":
         pytest.xfail("Segfault. Ticket 170877")
-    if model_id == "katuni4ka/tiny-random-flux" and model_type == "image-to-image":
+    if model_id == "optimum-intel-internal-testing/tiny-random-flux" and model_type == "image-to-image":
         pytest.xfail("Randomly wwb died with <Signals.SIGABRT: 6>. Ticket 170878")
 
     mac_arm64_skip = any(substring in model_id for substring in ('stable-diffusion-xl',

diff --git a/tools/who_what_benchmark/tests/test_cli_vlm.py b/tools/who_what_benchmark/tests/test_cli_vlm.py
@@ -96,7 +96,7 @@ def run_test(model_id, model_type, optimum_threshold, genai_threshold, tmp_path)
 @pytest.mark.parametrize(
     ("model_id", "model_type"),
     [
-        ("katuni4ka/tiny-random-llava", "visual-text"),
+        ("optimum-intel-internal-testing/tiny-random-llava", "visual-text"),
     ],
 )
 def test_vlm_basic(model_id, model_type, tmp_path):