Skip to main content

Manage models

tip

Recommended tutorials for setting up the local version

1. Add a model​

Download a Hugging Face model and save on your disk. In this tutorial, bert-large-uncased-whole-word-masking-finetuned-squad model will be downloaded from the Hugging Face Hub. It is a model finetuned on the SQuAD dataset. If the model is saved in ./bert-squad directory, we can upload it to our registry using the following command:

stochasticx models upload \
    --name "bert-squad" \
    --dir_path "./bert-squad" \
    --type "hf"
info
  • name: will allow you to identify the model later.
  • dir_path: directory path where your model is located.
  • type: model type. In this case a Hugging Face model

2. List and inspect your models​

You can list your models with the following command:

stochasticx models ls
CLI output
[+] Collecting all local models

┏━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━┳━━━━━━━━━━┓
┃ Id                       ┃ Name                    ┃ Directory path ┃ Type ┃ Uploaded ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━╇━━━━━━━━━━┩
│ 62e3a5aab5beb3002644093e │ bert-squad              │                │ hf   │ True     │
└──────────────────────────┴─────────────────────────┴────────────────┴──────┴──────────┘

To inspect this model further:

stochasticx models inspect --id "62e3a5aab5beb3002644093e"
CLI output
Model ID: 62e3a5aab5beb3002644093e ; Name: bert-squad ; Directory path: None ; Model type: hf ; Uploaded: True


{
   "model_type":"bert",
   "id2label":"None",
   "label2id":"None",
   "max_position_embeddings":512,
   "torch_dtype":"float32",
   "vocab_size":30522,
   "hugging_face_tasks":[
      "BertForQuestionAnswering"
   ],
   "model_size":1336507185,
   "specific_model_info":{
      "_name_or_path":"bert-large-uncased-whole-word-masking-finetuned-squad",
      "attention_probs_dropout_prob":0.1,
      "classifier_dropout":"None",
      "hidden_act":"gelu",
      "hidden_dropout_prob":0.1,
      "hidden_size":1024,
      "initializer_range":0.02,
      "intermediate_size":4096,
      "layer_norm_eps":1e-12,
      "num_attention_heads":16,
      "num_hidden_layers":24,
      "pad_token_id":0,
      "position_embedding_type":"absolute",
      "transformers_version":"4.18.0",
      "type_vocab_size":2,
      "use_cache":true
   }
}

3. Remove a model​

stochasticx models remove \
    --model_id "62e3a5aab5beb3002644093e"
info
  • model_id: id of the model to remove.