40 lines
1.0 KiB
JSON
40 lines
1.0 KiB
JSON
{
|
|
"_name_or_path": "/mnt/data1/model/base_model/Atom7B/checkpoint-101000-32kl",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_atom.LlamaConfig",
|
|
"AutoModel": "model_atom.LlamaForCausalLM",
|
|
"AutoModelForCausalLM": "model_atom.LlamaForCausalLM",
|
|
"AutoModelForSequenceClassification": "model_atom.LlamaForSequenceClassification"
|
|
},
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"max_length": 4096,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 32,
|
|
"pad_token_id": 2,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": {
|
|
"factor": 8.0,
|
|
"type": "dynamic"
|
|
},
|
|
"rope_theta": 500000,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.36.2",
|
|
"use_cache": true,
|
|
"vocab_size": 65000
|
|
}
|