checkpoint-5740/config.json

{
  "architectures": [
    "TraXLMistralForCausalLM"
  ],
  "dropout": 0.1,
  "dynamic_routing": true,
  "ff_expansion_factor": 4,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4"
  },
  "is_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4
  },
  "max_computation_steps": 5,
  "max_len": 256,
  "memory_size": 256,
  "model_type": "gpt2",
  "n_head": 4,
  "n_layer": 4,
  "rnn_units": 128,
  "sparse_attention": true,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "vocab_size": 50257
}