38 lines
920 B
JSON
38 lines
920 B
JSON
{
|
|
"JK": "last",
|
|
"_name_or_path": "/hpc2hdd/home/yli258/jhaidata/Graph-Reasoning-LLM/ckpts/llama_7b_rft_v1_k6",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"dropout_ratio": 0,
|
|
"end_token_id": 2,
|
|
"eos_token_id": 2,
|
|
"gnn_emb_dim": 300,
|
|
"gnn_type": "gin",
|
|
"graph_pooling": "mean",
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32,
|
|
"num_layer": 5,
|
|
"num_tasks": 1,
|
|
"pad_token_id": 2,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.36.2",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
}
|