| { | |
| "architectures": [ | |
| "ZhinaoForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attn_dropout_prob": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "configuration_zhinao.ZhinaoConfig", | |
| "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM" | |
| }, | |
| "bf16": true, | |
| "emb_dropout_prob": 0.1, | |
| "flah-attn_version": "2.5.5", | |
| "fp16": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.01, | |
| "intermediate_size": 13056, | |
| "log_logit": false, | |
| "max_position_embeddings": 365000, | |
| "model_max_length": 365000, | |
| "model_type": "zhinao", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 50000000.0, | |
| "switch": 0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.3", | |
| "use_cache": false, | |
| "use_flash_attn": true, | |
| "use_focal": false, | |
| "use_loss_weight": false, | |
| "use_pack_loss": false, | |
| "vocab_size": 158464 | |
| } | |