|
{ |
|
"model_type": "gptj", |
|
"vocab_size": 50257, |
|
"n_positions": 2048, |
|
"n_ctx": 2048, |
|
"n_embd": 4096, |
|
"n_layer": 28, |
|
"n_head": 16, |
|
"rotary_dim": 64, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-5, |
|
"bos_token_id": 50256, |
|
"eos_token_id": 50256, |
|
"pad_token_id": 50256, |
|
"task_specific_params": { |
|
"text-generation": { |
|
"do_sample": true, |
|
"max_length": 50 |
|
} |
|
}, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"num_return_sequences": 1, |
|
"chunk_size_feed_forward": 0, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false |
|
} |
|
|