43 lines
1.0 KiB
JSON
43 lines
1.0 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"OpensciForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": true,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_opensci.OpensciConfig",
|
||
|
|
"AutoModel": "modeling_opensci.OpensciModel",
|
||
|
|
"AutoModelForCausalLM": "modeling_opensci.OpensciForCausalLM"
|
||
|
|
},
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 2048,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8192,
|
||
|
|
"layer_norm_eps": 1e-05,
|
||
|
|
"max_position_embeddings": 16384,
|
||
|
|
"mlp_bias": true,
|
||
|
|
"model_type": "opensci",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 24,
|
||
|
|
"num_key_value_heads": 32,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"qk_layernorm": true,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_parameters": null,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 4.0,
|
||
|
|
"original_max_position_embeddings": 4096,
|
||
|
|
"rope_type": "yarn"
|
||
|
|
},
|
||
|
|
"rope_theta": 100000,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.51.3",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 50304
|
||
|
|
}
|