| { |
| "architectures": [ |
| "ZhinaoForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_zhinao.ZhinaoConfig", |
| "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM" |
| }, |
| "bf16": true, |
| "fp16": false, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.01, |
| "intermediate_size": 11008, |
| "max_position_embeddings": 4096, |
| "model_max_length": 4096, |
| "model_type": "zhinao", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.38.2", |
| "use_cache": false, |
| "use_flash_attn": "auto", |
| "vocab_size": 158464 |
| } |
|
|
