Multi-Domain-Expert-Learning/falcon1b
018
1{2 "_name_or_path": "student1/",3 "alibi": false,4 "apply_residual_connection_post_layernorm": false,5 "architectures": [6 "RWForCausalLM"7 ],8 "attention_dropout": 0.0,9 "auto_map": {10 "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",11 "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",12 "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",13 "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",14 "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",15 "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"16 },17 "bias": false,18 "bos_token_id": 11,19 "eos_token_id": 11,20 "hidden_dropout": 0.0,21 "hidden_size": 4544,22 "init_metadata": {23 "copied_decoder_layers": [24 0,25 4,26 8,27 12,28 16,29 20,30 24,31 3132 ],33 "teacher_type": "RefinedWebModel"34 },35 "initializer_range": 0.02,36 "layer_norm_epsilon": 1e-05,37 "model_type": "RefinedWebModel",38 "multi_query": true,39 "n_head": 71,40 "n_layer": 8,41 "output_hidden_states": true,42 "parallel_attn": true,43 "torch_dtype": "bfloat16",44 "transformers_version": "4.30.1",45 "use_cache": true,46 "vocab_size": 6502447}48 