{ | |
"_name_or_path": "gmonsoon/MiniCPM-2B-Base-v3", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 1, | |
"dim_model_base": 256, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 2304, | |
"initializer_range": 0.1, | |
"intermediate_size": 5760, | |
"max_position_embeddings": 2048, | |
"model_type": "llama", | |
"num_attention_heads": 36, | |
"num_hidden_layers": 40, | |
"num_key_value_heads": 36, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"scale_depth": 1.4, | |
"scale_emb": 12, | |
"tie_word_embeddings": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.37.2", | |
"use_cache": true, | |
"vocab_size": 122753 | |
} | |