jweb's picture
Upload config.json
36fdf15
raw history blame
No virus
1.85 kB
{
"_name_or_path": "/home/mycat/model/rinna/finetuned_natume",
"activation_function": "gelu_fast",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 2,
"d_ff": 2048,
"d_kv": 64,
"d_model": 2048,
"dropout_rate": 0.1,
"embd_pdrop": 0.1,
"eos_token_id": 3,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 2048,
"n_head": 16,
"n_inner": 8192,
"n_layer": 24,
"n_positions": 1024,
"num_beams": 4,
"num_heads": 16,
"num_layers": 24,
"relative_attention_num_buckets": 32,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
},
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 200,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": "summarize: "
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to German: "
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to French: "
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to Romanian: "
}
},
"torch_dtype": "float16",
"transformers_version": "4.17.0.dev0",
"use_cache": false,
"vocab_size": 44876
}