| { | |
| "architectures": [ | |
| "Step1ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_step1.Step1Config", | |
| "AutoModelForCausalLM": "modeling_step1.Step1ForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 3, | |
| "hidden_size": 3072, | |
| "intermediate_size": 8192, | |
| "max_seq_len": 32768, | |
| "model_type": "step1", | |
| "num_attention_groups": 4, | |
| "num_attention_heads": 48, | |
| "num_hidden_layers": 32, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.53.3", | |
| "use_cache": true, | |
| "vocab_size": 74752 | |
| } | |