SparseLLM/ProSparse-MiniCPM-1B-sft
3555
1{2 "_name_or_path": "SparseLLM/ProSparse-MiniCPM-1B-sft",3 "architectures": [4 "MiniCPMForCausalLM"5 ],6 "auto_map": {7 "AutoConfig": "configuration_minicpm.MiniCPMConfig",8 "AutoModel": "modeling_minicpm.MiniCPMModel",9 "AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM",10 "AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM",11 "AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification"12 },13 "bos_token_id": 1,14 "eos_token_id": 2,15 "hidden_act": "fatrelu",16 "hidden_act_param": 0.03,17 "hidden_size": 1536,18 "initializer_range": 0.1,19 "intermediate_size": 3840,20 "max_position_embeddings": 4096,21 "num_attention_heads": 24,22 "num_hidden_layers": 52,23 "num_key_value_heads": 8,24 "rms_norm_eps": 1e-05,25 "rope_scaling": null,26 "torch_dtype": "bfloat16",27 "transformers_version": "4.36.0",28 "use_cache": true,29 "vocab_size": 73440,30 "scale_emb": 12,31 "dim_model_base": 256,32 "scale_depth": 1.433}34 