zai-org/glm-2b
16150
1{2 "_name_or_path": "THUDM/glm-2b",3 "architectures": [4 "GLMModel"5 ],6 "attention_dropout_prob": 0.1,7 "attention_scale": 1.0,8 "auto_map": {9 "AutoConfig": "configuration_glm.GLMConfig",10 "AutoModel": "modeling_glm.GLMModel",11 "AutoModelForSeq2SeqLM": "modeling_glm.GLMForConditionalGeneration",12 "AutoModelForMultipleChoice": "modeling_glm.GLMForMultipleChoice",13 "AutoModelForSequenceClassification": "modeling_glm.GLMForSequenceClassification"14 },15 "block_position_encoding": true,16 "checkpoint_activations": false,17 "checkpoint_num_layers": 1,18 "embedding_dropout_prob": 0.1,19 "hidden_size": 2048,20 "initializer_range": 0.02,21 "max_sequence_length": 1024,22 "model_type": "glm",23 "num_attention_heads": 32,24 "num_layers": 36,25 "output_dropout_prob": 0.1,26 "output_predict": true,27 "parallel_output": true,28 "pool_token": "cls",29 "relative_encoding": false,30 "spell_func": "lstm",31 "spell_length": null,32 "torch_dtype": "float32",33 "transformers_version": "4.23.1",34 "vocab_size": 5030435}36 