# Rasa BERT, load weights from cache **URL:** \ **Category:** Rasa Open Source\ **Created:** [April 24, 2020, 11:14am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989 "2020-04-24T11:14:47Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![almois](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/almois/32/8295_2.png) [@almois](https://forum.rasa.com/u/almois)\ **Post date:** [April 24, 2020, 11:14am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/1 "2020-04-24T11:14:47Z")
Hi everyone, Due to some restrictions, during the BERT training I am not allowed to load the weights etc. from external sources. So, I pre-loaded them and stored in the cache from where the Rasa can read i.e. access them. Now, when I am starting the model locally it is working fine (and loads the weights etc for the model from cache). However, when I am doing the same thing inside the docker container I am getting the following error: ``` INFO transformers.modeling_tf_utils - loading weights file [https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-tf_model.h5](https://urldefense.proofpoint.com/v2/url?u=https-3A__s3.amazonaws.com_models.huggingface.co_bert_bert-2Dbase-2Dmultilingual-2Duncased-2Dtf-5Fmodel.h5&d=DwQFAw&c=eIGjsITfXP_y-DLLX0uEHXJvU8nOHrUK8IrwNKOtkVU&r=8Sh_uRlXH-MR-JleoFcjs3fOU3krvhtAtBPw5MwlNpc&m=wbAACKHoUduiwjeLs-7QP88f9t6CDS-I7GDDWhSrBjA&s=yIKz-GdmrR27-hp7JnFOK8P9gEzt84jwMTRdtapY6f4&e=) from cache at None ERROR rasa.core.agent - Could not load model due to stat: path should be string, bytes, os.PathLike or integer, not NoneType. ``` This only happens with weights so far. so the vocab and config files are loaded without any problems. Does anyone had the same issue before? Or may be some one has any idea to fix it? Appreciate any help! ---
**Author:** ![akelad](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/akelad/32/69_2.png) [@akelad](https://forum.rasa.com/u/akelad)\ **Post date:** [April 27, 2020, 11:13am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/2 "2020-04-27T11:13:16Z")
Hey @almois are you setting the location of the weights through an environment envariable or how? ---
**Author:** ![nboussarsar](https://avatars.discourse-cdn.com/v4/letter/n/f08c70/32.png) [@nboussarsar](https://forum.rasa.com/u/nboussarsar)\ **Post date:** [April 28, 2020, 8:31am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/3 "2020-04-28T08:31:09Z")
Hi @akelad, thanks for responding. I am supporting @almois on this topic. We are setting the weights location through the `config.yml` file ``` pipeline: - name: HFTransformersNLP model_name: "bert" model_weights: "bert-base-multilingual-uncased" cache_dir: lfs ``` To develop further the issue described by @almois, we are running Rasa as a docker container and it looks like it is a “machine/environment” specific issue as the error is thrown in one environment but not in another one. As per our understanding, the error is the following: `rasa.core.agent` is trying to load a file from a path which is set to `None`. Please see the logs below. ``` DEBUG rasa.nlu.utils.hugging_face.hf_transformers - Loading Tokenizer and Model for bert INFO transformers.tokenization_utils - loading file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt from cache at lfs/ bb773818882b0524dc53a1b31a2cc95bc489f000e7e19773ba07846011a6c711.535306b226c42cebebbc0dabc83b92ab11260e9919e21e2ab0beb301f267b4c7 INFO transformers.configuration_utils - loading configuration file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-config.json from cache at lfs/ 33b56ce0f312e47e4d77a57791a4fc6233ae4a560dd2bdd186107058294e58ab.c7892120c5a9b21e515abc904e398dbabddf9510b122f659063cbf361fe16868 . . . INFO transformers.modeling_tf_utils - loading weights file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-tf_model.h5 from cache at None ERROR rasa.core.agent - Could not load model due to stat: path should be string, bytes, os.PathLike or integer, not NoneType. ``` As you can see in the logs, `transformers.tokenization_utils` and `transformers.configuration_utils` were able to locate the folder `lfs` which contains the bert cached files. On the other hand, `transformers.modeling_tf_utils` was not able to as the folder was set to `None`. Please let me know if you need to have a look on the Dockerfile. ---
**Author:** ![nboussarsar](https://avatars.discourse-cdn.com/v4/letter/n/f08c70/32.png) [@nboussarsar](https://forum.rasa.com/u/nboussarsar)\ **Post date:** [April 28, 2020, 9:00pm UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/4 "2020-04-28T21:00:16Z")
SOLVED When we run the docker image, rasa needs to download files (in addition to the ones already cached) and if there is no internet access, then it will thrown the `None` folder. ---
**Author:** ![argideritzalpea](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/argideritzalpea/32/7528_2.png) [@argideritzalpea](https://forum.rasa.com/u/argideritzalpea)\ **Post date:** [May 4, 2020, 1:47am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/5 "2020-05-04T01:47:07Z")
How does one resolve this issue when you train a Bert model in one docker environment, and then curl that resulting model to Rasa X in a different docker container? > [@Rasa X Training Error](http://forum.rasa.com/t/rasa-x-training-error/27143): > > So I have set up Rasa-X on an AWS EC2 instance and all was going well until I started using ‘HFTransformersNLP’. Now I get errors saying: File “/opt/venv/lib/python3.6/site-packages/transformers/tokenization\_utils.py”, line 400, in \_from\_pretrained raise EnvironmentError(msg) OSError: Couldn’t reach server at ‘{}’ to download vocabulary files. and File "/usr/local/lib/python3.6/os.py", line 220, in makedirs mkdir(name, mode) PermissionError: [Errno 13] Permission denied: '/.cache' from th… ---
**Author:** ![localk](https://avatars.discourse-cdn.com/v4/letter/l/8e8cbc/32.png) [@localk](https://forum.rasa.com/u/localk)\ **Post date:** [October 30, 2020, 7:44am UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/6 "2020-10-30T07:44:41Z")
Then there is no way to use HFTransformerNLP without a network? ---
**Author:** ![akelad](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/akelad/32/69_2.png) [@akelad](https://forum.rasa.com/u/akelad)\ **Post date:** [October 30, 2020, 1:16pm UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/7 "2020-10-30T13:16:30Z")
If you specify a `cache_dir`, you should only need to download it once. [Components](https://rasa.com/docs/rasa/components#hftransformersnlp) ---
**Author:** ![evilc3](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/evilc3/32/14300_2.png) [@evilc3](https://forum.rasa.com/u/evilc3)\ **Post date:** [May 30, 2021, 5:07pm UTC](https://forum.rasa.com/t/rasa-bert-load-weights-from-cache/27989/8 "2021-05-30T17:07:37Z")
@akelad , I am facing a similar issue when ever I sepcify a cache\_dir then it downloads the file but when I turn off my internet i get connection error sayinh cant load model weights not cached shouldn’t it load from the cache\_dir. Right ? Using rasa 2.6 I am not using languagetokebizer and hftransformernlp as d docs says its deprecated.is something wrong with my config maybe ? Here is my config file. ``` Configuration for Rasa NLU. pipeline: - name: sentiment_ex.SentimentEmotionAnalyzerNLTK - name: WhitespaceTokenizer - name: RegexFeaturizer - name: LexicalSyntacticFeaturizer # - name: CountVectorsFeaturizer # Analyzer to use, either 'word', 'char', or 'char_wb' # "analyzer": "word" # Set the lower and upper boundaries for the n-grams # "min_ngram": 1 # "max_ngram": 3 # Set the out-of-vocabulary token # "OOV_token": "_oov_" # Whether to use a shared vocab # "use_shared_vocab": False - name: LanguageModelFeaturizer # Name of the language model to use model_name: "bert" # Pre-Trained weights to be loaded model_weights: "rasa/LaBSE" cache_dir: /dir_name/model_name - name: RegexEntityExtractor case_sensitive: False use_lookup_tables: True - name: "DucklingEntityExtractor" # url of the running duckling server url: "http://localhost:8000" # # dimensions to extract dimensions: ["time","email"] timeout : 3 - name: DIETClassifier epochs: 150 constrain_similarities: true # model_confidence: linear_norm - name: EntitySynonymMapper - name: ResponseSelector epochs: 100 retrieval_intent: faq # scale_loss: false - name: ResponseSelector epochs: 100 retrieval_intent: chitchat # scale_loss: false - name: ResponseSelector epochs: 100 retrieval_intent: inform scale_loss: false - name: FallbackClassifier threshold: 0.70 ambiguity_threshold: 0.1 ``` I just want to train d model without using internet 😭. and during debggingit y is it making api request to hugging face ?