{ | |
"_name_or_path": "config/pythia-14m", | |
"architectures": [ | |
"GPTNeoXForCausalLM" | |
], | |
"attention_bias": true, | |
"attention_dropout": 0.0, | |
"bos_token_id": 1, | |
"classifier_dropout": 0.1, | |
"eos_token_id": 2, | |
"hidden_act": "gelu", | |
"hidden_dropout": 0.0, | |
"hidden_size": 128, | |
"initializer_range": 0.02, | |
"intermediate_size": 512, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 512, | |
"model_type": "gpt_neox", | |
"num_attention_heads": 4, | |
"num_hidden_layers": 6, | |
"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": "float32", | |
"transformers_version": "4.45.1", | |
"use_cache": false, | |
"use_parallel_residual": true, | |
"vocab_size": 49953 | |
} | |