初始化项目,由ModelHub XC社区提供模型
Model: Fengshenbang/Wenzhong-GPT2-3.5B Source: Original Platform
This commit is contained in:
85
configuration.json
Normal file
85
configuration.json
Normal file
@@ -0,0 +1,85 @@
|
||||
{
|
||||
"task": "text-generation",
|
||||
"framework": "pytorch",
|
||||
"preprocessor": {
|
||||
"type": "text-gen-tokenizer",
|
||||
"padding": false
|
||||
},
|
||||
"model": {
|
||||
"type": "text-generation",
|
||||
"do_sample": true,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"max_length": 100,
|
||||
"repetition_penalty": 1,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"pad_token_id": 0,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"num_beams": 1,
|
||||
"num_beam_groups": 1,
|
||||
"length_penalty": 1.0,
|
||||
"diversity_penalty": 0.0,
|
||||
"early_stopping": false,
|
||||
"num_return_sequences": 1,
|
||||
"output_scores": false,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"return_dict_in_generate": false,
|
||||
"is_encoder_decoder": false,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"bad_words_ids": null,
|
||||
"min_length": 0,
|
||||
"remove_invalid_values": false,
|
||||
"temperature": 1.0,
|
||||
"shared_embedding": true,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"suppress_tokens": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"typical_p": 1.0,
|
||||
"backbone": {
|
||||
"type": "gpt2",
|
||||
"prefix": "transformer",
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_layer": 12,
|
||||
"n_positions": 1024,
|
||||
"resid_pdrop": 0.1,
|
||||
"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
|
||||
}
|
||||
},
|
||||
"vocab_size": 50257
|
||||
},
|
||||
"head": {
|
||||
"type": "text-generation",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"vocab_size": 50257,
|
||||
"hidden_size": 768
|
||||
}
|
||||
},
|
||||
"pipeline": {
|
||||
"type": "text-generation"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user