| { | |
| "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": 32768, | |
| "model_max_length": 32768, | |
| "model_type": "zhinao", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "quantization_config": { | |
| "bits": 4, | |
| "checkpoint_format": "gptq", | |
| "damp_percent": 0.01, | |
| "desc_act": false, | |
| "group_size": 128, | |
| "model_file_base_name": "gptq_model-4bit-128g", | |
| "model_name_or_path": "360Zhinao-7B-Chat-32K-Int4", | |
| "quant_method": "gptq", | |
| "static_groups": false, | |
| "sym": true, | |
| "true_sequential": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 50000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "use_flash_attn": "auto", | |
| "vocab_size": 158464 | |
| } | |