35 lines
877 B
JSON
35 lines
877 B
JSON
|
{
|
||
|
|
"_flash_attn_2_enabled": true,
|
||
|
|
"_name_or_path": "./model/Orion-14B-Chat",
|
||
|
|
"architectures": [
|
||
|
|
"OrionForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_orion.OrionConfig",
|
||
|
|
"AutoModelForCausalLM": "modeling_orion.OrionForCausalLM"
|
||
|
|
},
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 15360,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"max_sequence_length": 4096,
|
||
|
|
"model_type": "orion",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"num_key_value_heads": 40,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.37.1",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 84608
|
||
|
|
}
|