| { | |
| "vocab_size": 49152, | |
| "n_positions": 8192, | |
| "n_embd": 6144, | |
| "n_layer": 40, | |
| "n_head": 48, | |
| "n_inner": 24576, | |
| "activation_function": "gelu", | |
| "resid_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "attn_pdrop": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "initializer_range": 0.02, | |
| "scale_attn_weights": true, | |
| "use_cache": true, | |
| "attention_softmax_in_fp32": true, | |
| "scale_attention_softmax_in_fp32": true, | |
| "multi_query": true, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "output_attentions": false, | |
| "torchscript": false, | |
| "torch_dtype": "float32", | |
| "use_bfloat16": false, | |
| "tf_legacy_loss": false, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "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, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "architectures": [ | |
| "LoRDCoderForCausalLM" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "gate_dim": 2304, | |
| "auto_map": { | |
| "AutoConfig": "configuration_lordcoder_v0.LoRDCoderConfig", | |
| "AutoModelForCausalLM": "modeling_lordcoder_v0.LoRDCoderForCausalLM" | |
| }, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "pad_token_id": null, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "transformers_version": "4.32.0.dev0", | |
| "inference_runner": 0, | |
| "max_batch_size": null, | |
| "max_sequence_length": null, | |
| "model_type": "lordcoder", | |
| "pad_key_length": true, | |
| "pre_allocate_kv_cache": false, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "validate_runner_input": true, | |
| "lord_config": { | |
| "mlp.c_proj": "directLoRD_double_bias" | |
| } | |
| } |