Launch Error #51
Description
Hello,
Thanks for the great project!
I'm facing some issue when running the app, which looks like this.
- It doesn't work even trying
export LLM_TYPE="huggingface-inference-api"
(data) dj475@lambda1:~/yalenlp$ export HF_TOKEN=""
(data) dj475@lambda1:~/yalenlp$ python data_aug_test_250901.py
/home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/constants.py:132: UserWarning: ARGILLA_API_URL or ARGILLA_API_KEY is not set or is empty
warnings.warn("ARGILLA_API_URL or ARGILLA_API_KEY is not set or is empty")
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/huggingface_hub/utils/_http.py:406 │
│ in hf_raise_for_status │
│ │
│ 403 │ </Tip> │
│ 404 │ """ │
│ 405 │ try: │
│ ❱ 406 │ │ response.raise_for_status() │
│ 407 │ except HTTPError as e: │
│ 408 │ │ error_code = response.headers.get("X-Error-Code") │
│ 409 │ │ error_message = response.headers.get("X-Error-Message") │
│ │
│ ╭───────────── locals ─────────────╮ │
│ │ endpoint_name = None │ │
│ │ error_code = None │ │
│ │ error_message = None │ │
│ │ response = <Response [404]> │ │
│ ╰──────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/requests/models.py:1026 in │
│ raise_for_status │
│ │
│ 1023 │ │ │ ) │
│ 1024 │ │ │
│ 1025 │ │ if http_error_msg: │
│ ❱ 1026 │ │ │ raise HTTPError(http_error_msg, response=self) │
│ 1027 │ │
│ 1028 │ def close(self): │
│ 1029 │ │ """Releases the connection back to the pool. Once this method has been │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ http_error_msg = '404 Client Error: Not Found for url: │ │
│ │ https://api-inference.huggingface.co/status'+38 │ │
│ │ reason = 'Not Found' │ │
│ │ self = <Response [404]> │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
HTTPError: 404 Client Error: Not Found for url: https://api-inference.huggingface.co/status/meta-llama/Meta-Llama-3.1-8B-Instruct
The above exception was the direct cause of the following exception:
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/pipeli │
│ nes/base.py:177 in <module> │
│ │
│ 174 │
│ 175 try: │
│ 176 │ llm = _get_llm() │
│ ❱ 177 │ llm.load() │
│ 178 │ llm.generate([[{"content": "Hello, world!", "role": "user"}]]) │
│ 179 except Exception as e: │
│ 180 │ raise Exception(f"Error loading {llm.__class__.__name__}: {e}") │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ API_KEYS = [''] │ │
│ │ DEFAULT_BATCH_SIZE = 5 │ │
│ │ HUGGINGFACE_BASE_URL = None │ │
│ │ HUGGINGFACE_BASE_URL_COMPLETION = None │ │
│ │ llm = InferenceEndpointsLLM( │ │
│ │ │ use_magpie_template=False, │ │
│ │ │ magpie_pre_query_template=None, │ │
│ │ │ generation_kwargs={}, │ │
│ │ │ use_offline_batch_generation=False, │ │
│ │ │ offline_batch_generation_block_until_done=None, │ │
│ │ │ jobs_ids=None, │ │
│ │ │ model_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ endpoint_name=None, │ │
│ │ │ endpoint_namespace=None, │ │
│ │ │ base_url=None, │ │
│ │ │ api_key=SecretStr('**********'), │ │
│ │ │ tokenizer_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ model_display_name=None, │ │
│ │ │ structured_output=None │ │
│ │ ) │ │
│ │ math = <module 'math' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/lib-dynl… │ │
│ │ MODEL = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ MODEL_COMPLETION = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ OLLAMA_BASE_URL = None │ │
│ │ OLLAMA_BASE_URL_COMPLETION = None │ │
│ │ OPENAI_BASE_URL = None │ │
│ │ OPENAI_BASE_URL_COMPLETION = None │ │
│ │ random = <module 'random' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/random.p… │ │
│ │ TOKEN_INDEX = 1 │ │
│ │ TOKENIZER_ID = None │ │
│ │ TOKENIZER_ID_COMPLETION = None │ │
│ │ VLLM_BASE_URL = None │ │
│ │ VLLM_BASE_URL_COMPLETION = None │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/distilabel/models/llms/huggingface │
│ /inference_endpoints.py:164 in load │
│ │
│ 161 │ │ # Sets the logger and calls the load method of the BaseClient │
│ 162 │ │ self._num_generations_param_supported = False │
│ 163 │ │ AsyncLLM.load(self) │
│ ❱ 164 │ │ InferenceEndpointsBaseClient.load(self) │
│ 165 │ │
│ 166 │ @model_validator(mode="after") # type: ignore │
│ 167 │ def only_one_of_model_id_endpoint_name_or_base_url_provided( │
│ │
│ ╭───────────────────────────── locals ─────────────────────────────╮ │
│ │ self = InferenceEndpointsLLM( │ │
│ │ │ use_magpie_template=False, │ │
│ │ │ magpie_pre_query_template=None, │ │
│ │ │ generation_kwargs={}, │ │
│ │ │ use_offline_batch_generation=False, │ │
│ │ │ offline_batch_generation_block_until_done=None, │ │
│ │ │ jobs_ids=None, │ │
│ │ │ model_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ endpoint_name=None, │ │
│ │ │ endpoint_namespace=None, │ │
│ │ │ base_url=None, │ │
│ │ │ api_key=SecretStr('**********'), │ │
│ │ │ tokenizer_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ model_display_name=None, │ │
│ │ │ structured_output=None │ │
│ │ ) │ │
│ ╰──────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/distilabel/models/base_clients/inf │
│ erence_endpoints.py:101 in load │
│ │
│ 98 │ │ │ client = InferenceClient( │
│ 99 │ │ │ │ model=self.model_id, token=self.api_key.get_secret_value() │
│ 100 │ │ │ ) │
│ ❱ 101 │ │ │ status = client.get_model_status() │
│ 102 │ │ │ │
│ 103 │ │ │ if ( │
│ 104 │ │ │ │ status.state not in {"Loadable", "Loaded"} │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ client = <InferenceClient(model='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ timeout=None)> │ │
│ │ get_inference_endpoint = <bound method HfApi.get_inference_endpoint of │ │
│ │ <huggingface_hub.hf_api.HfApi object at 0x7fab8a709d90>> │ │
│ │ self = InferenceEndpointsLLM( │ │
│ │ │ use_magpie_template=False, │ │
│ │ │ magpie_pre_query_template=None, │ │
│ │ │ generation_kwargs={}, │ │
│ │ │ use_offline_batch_generation=False, │ │
│ │ │ offline_batch_generation_block_until_done=None, │ │
│ │ │ jobs_ids=None, │ │
│ │ │ model_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ endpoint_name=None, │ │
│ │ │ endpoint_namespace=None, │ │
│ │ │ base_url=None, │ │
│ │ │ api_key=SecretStr('**********'), │ │
│ │ │ tokenizer_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ model_display_name=None, │ │
│ │ │ structured_output=None │ │
│ │ ) │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/huggingface_hub/inference/_client. │
│ py:3155 in get_model_status │
│ │
│ 3152 │ │ url = f"{INFERENCE_ENDPOINT}/status/{model}" │
│ 3153 │ │ │
│ 3154 │ │ response = get_session().get(url, headers=self.headers) │
│ ❱ 3155 │ │ hf_raise_for_status(response) │
│ 3156 │ │ response_data = response.json() │
│ 3157 │ │ │
│ 3158 │ │ if "error" in response_data: │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ model = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ response = <Response [404]> │ │
│ │ self = <InferenceClient(model='meta-llama/Meta-Llama-3.1-8B-Instruct', timeout=None)> │ │
│ │ url = 'https://api-inference.huggingface.co/status/meta-llama/Meta-Llama-3.1-8B-Instru… │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/huggingface_hub/utils/_http.py:477 │
│ in hf_raise_for_status │
│ │
│ 474 │ │ │
│ 475 │ │ # Convert `HTTPError` into a `HfHubHTTPError` to display request information │
│ 476 │ │ # as well (request id and/or server error message) │
│ ❱ 477 │ │ raise _format(HfHubHTTPError, str(e), response) from e │
│ 478 │
│ 479 │
│ 480 def _format(error_type: Type[HfHubHTTPError], custom_message: str, response: Response) - │
│ │
│ ╭───────────── locals ─────────────╮ │
│ │ endpoint_name = None │ │
│ │ error_code = None │ │
│ │ error_message = None │ │
│ │ response = <Response [404]> │ │
│ ╰──────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
HfHubHTTPError: 404 Client Error: Not Found for url: https://api-inference.huggingface.co/status/meta-llama/Meta-Llama-3.1-8B-Instruct
(Request ID: Root=1-68b55e8e-30b43de1548a697b564e3515;fc6d6db8-cacd-4f0f-9aa8-dfbfb0270682)
During handling of the above exception, another exception occurred:
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /storage/home/dj475/yalenlp/data_aug_test_250901.py:3 in <module> │
│ │
│ 1 from synthetic_dataset_generator import launch │
│ 2 │
│ ❱ 3 launch() │
│ 4 │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/__init │
│ __.py:14 in launch │
│ │
│ 11 │ Based on the `TabbedInterface` from Gradio. │
│ 12 │ Parameters: https://www.gradio.app/docs/gradio/tabbedinterface │
│ 13 │ """ │
│ ❱ 14 │ from synthetic_dataset_generator.app import demo │
│ 15 │ return demo.launch(*args, server_name="0.0.0.0", **kwargs) │
│ 16 │
│ 17 │
│ │
│ ╭── locals ───╮ │
│ │ args = () │ │
│ │ kwargs = {} │ │
│ ╰─────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/app.py │
│ :4 in <module> │
│ │
│ 1 from synthetic_dataset_generator._tabbedinterface import TabbedInterface │
│ 2 │
│ 3 # from synthetic_dataset_generator.apps.eval import app as eval_app │
│ ❱ 4 from synthetic_dataset_generator.apps.rag import app as rag_app │
│ 5 from synthetic_dataset_generator.apps.about import app as about_app │
│ 6 from synthetic_dataset_generator.apps.chat import app as chat_app │
│ 7 from synthetic_dataset_generator.apps.textcat import app as textcat_app │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/apps/r │
│ ag.py:33 in <module> │
│ │
│ 30 │ MODEL_COMPLETION, │
│ 31 │ SAVE_LOCAL_DIR, │
│ 32 ) │
│ ❱ 33 from synthetic_dataset_generator.pipelines.base import get_rewritten_prompts │
│ 34 from synthetic_dataset_generator.pipelines.embeddings import ( │
│ 35 │ get_embeddings, │
│ 36 │ get_sentence_embedding_dimensions, │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ DEFAULT_BATCH_SIZE = 5 │ │
│ │ gr = <module 'gradio' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/gradio/… │ │
│ │ MODEL = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ MODEL_COMPLETION = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ nltk = <module 'nltk' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/nltk/__… │ │
│ │ os = <module 'os' (frozen)> │ │
│ │ pd = <module 'pandas' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/pandas/… │ │
│ │ random = <module 'random' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/random.py'> │ │
│ │ rg = <module 'argilla' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/argilla… │ │
│ │ SAVE_LOCAL_DIR = None │ │
│ │ Union = typing.Union │ │
│ │ uuid = <module 'uuid' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/uuid.py'> │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/dj475/miniconda3/envs/data/lib/python3.12/site-packages/synthetic_dataset_generator/pipeli │
│ nes/base.py:180 in <module> │
│ │
│ 177 │ llm.load() │
│ 178 │ llm.generate([[{"content": "Hello, world!", "role": "user"}]]) │
│ 179 except Exception as e: │
│ ❱ 180 │ raise Exception(f"Error loading {llm.__class__.__name__}: {e}") │
│ 181 │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ API_KEYS = [''] │ │
│ │ DEFAULT_BATCH_SIZE = 5 │ │
│ │ HUGGINGFACE_BASE_URL = None │ │
│ │ HUGGINGFACE_BASE_URL_COMPLETION = None │ │
│ │ llm = InferenceEndpointsLLM( │ │
│ │ │ use_magpie_template=False, │ │
│ │ │ magpie_pre_query_template=None, │ │
│ │ │ generation_kwargs={}, │ │
│ │ │ use_offline_batch_generation=False, │ │
│ │ │ offline_batch_generation_block_until_done=None, │ │
│ │ │ jobs_ids=None, │ │
│ │ │ model_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ endpoint_name=None, │ │
│ │ │ endpoint_namespace=None, │ │
│ │ │ base_url=None, │ │
│ │ │ api_key=SecretStr('**********'), │ │
│ │ │ tokenizer_id='meta-llama/Meta-Llama-3.1-8B-Instruct', │ │
│ │ │ model_display_name=None, │ │
│ │ │ structured_output=None │ │
│ │ ) │ │
│ │ math = <module 'math' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/lib-dynl… │ │
│ │ MODEL = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ MODEL_COMPLETION = 'meta-llama/Meta-Llama-3.1-8B-Instruct' │ │
│ │ OLLAMA_BASE_URL = None │ │
│ │ OLLAMA_BASE_URL_COMPLETION = None │ │
│ │ OPENAI_BASE_URL = None │ │
│ │ OPENAI_BASE_URL_COMPLETION = None │ │
│ │ random = <module 'random' from │ │
│ │ '/home/dj475/miniconda3/envs/data/lib/python3.12/random.p… │ │
│ │ TOKEN_INDEX = 1 │ │
│ │ TOKENIZER_ID = None │ │
│ │ TOKENIZER_ID_COMPLETION = None │ │
│ │ VLLM_BASE_URL = None │ │
│ │ VLLM_BASE_URL_COMPLETION = None │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
Exception: Error loading InferenceEndpointsLLM: 404 Client Error: Not Found for url:
https://api-inference.huggingface.co/status/meta-llama/Meta-Llama-3.1-8B-Instruct (Request ID:
Root=1-68b55e8e-30b43de1548a697b564e3515;fc6d6db8-cacd-4f0f-9aa8-dfbfb0270682)