GraphGPT-7B-mix-all / config.json
Jiabin99's picture
Update config.json
5d66a0d
{
"_name_or_path": "../vicuna-7b-v1.5-16k",
"architectures": [
"GraphLlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_graph_mlp_adapter": false,
"graph_hidden_size": 128,
"graph_select_layer": -2,
"graph_tower": "clip_gt_arxiv_pub",
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"max_sequence_length": 16384,
"model_type": "GraphLlama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretrain_graph_model_path": "./clip_gt_arxiv_pub",
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"sep_graph_conv_front": false,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"tune_graph_mlp_adapter": true,
"use_cache": false,
"use_graph_proj": true,
"use_graph_start_end": true,
"vocab_size": 32003
}