huggingtweets/java_jigga
024
1{2 "_name_or_path": "gpt2",3 "activation_function": "gelu_new",4 "architectures": [5 "GPT2LMHeadModel"6 ],7 "attn_pdrop": 0.1,8 "bos_token_id": 50256,9 "embd_pdrop": 0.1,10 "eos_token_id": 50256,11 "gradient_checkpointing": false,12 "initializer_range": 0.02,13 "layer_norm_epsilon": 1e-05,14 "model_type": "gpt2",15 "n_ctx": 1024,16 "n_embd": 768,17 "n_head": 12,18 "n_inner": null,19 "n_layer": 12,20 "n_positions": 1024,21 "resid_pdrop": 0.1,22 "summary_activation": null,23 "summary_first_dropout": 0.1,24 "summary_proj_to_labels": true,25 "summary_type": "cls_index",26 "summary_use_proj": true,27 "task_specific_params": {28 "text-generation": {29 "do_sample": true,30 "max_length": 160,31 "min_length": 10,32 "prefix": "<|endoftext|>",33 "temperature": 1.0,34 "top_p": 0.9535 }36 },37 "transformers_version": "4.5.0",38 "use_cache": true,39 "vocab_size": 5025740}41 