MATH-LLM-72B / config.json
ALmonster's picture
Upload 10 files
1d38fd1 verified
{
"_name_or_path": "/root/lwt/tech/mcmd-72b",
"architectures": [
"mcmdForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_mcmd.mcmdConfig",
"AutoModel": "modeling_mcmd.mcmdForCausalLM",
"AutoModelForCausalLM": "modeling_mcmd.mcmdForCausalLM"
},
"clip_path": "/data1/model/DFN5B-CLIP-ViT-H-14-378",
"hidden_size": 8192,
"hidden_sizes": 8192,
"input_img_size": 378,
"lm_model": {
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 29696,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
},
"lm_path": "/data1/model/Qwen2-72B-Instruct",
"max_length": 1024,
"model_type": "mcmd",
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"vision_config": "mlp2x_gelu",
"vocab_size": 152064
}