初始化项目,由ModelHub XC社区提供模型
Model: abehandlerorg/pythia-45m_lr1e-3_steps5k_seed2_interleave0.02 Source: Original Platform
This commit is contained in:
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 512,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"is_decoder": false,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 6,
|
||||
"pad_token_id": null,
|
||||
"rope_parameters": {
|
||||
"partial_rotary_factor": 0.25,
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.1.0",
|
||||
"use_cache": false,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
Reference in New Issue
Block a user