|
{ |
|
"_name_or_path": "models/GPTNeoX-160m", |
|
"architectures": [ |
|
"GPTNeoXForCausalLM" |
|
], |
|
"attention_bias": true, |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "config_custom.GPTNeoXConfig", |
|
"AutoModel": "modeling_custom.GPTNeoXModel", |
|
"AutoModelForCausalLM": "modeling_custom.GPTNeoXForCausalLM" |
|
}, |
|
"bos_token_id": 0, |
|
"classifier_dropout": 0.1, |
|
"eos_token_id": 0, |
|
"hidden_act": "gelu", |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "gpt_neox", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"partial_rotary_factor": 0.25, |
|
"rope_scaling": null, |
|
"rope_theta": 10000, |
|
"rotary_emb_base": 10000, |
|
"rotary_pct": 0.25, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.45.0", |
|
"use_cache": true, |
|
"use_parallel_residual": true, |
|
"vocab_size": 50304 |
|
} |
|
|