| { | |
| "_name_or_path": "./co_output_model", | |
| "architectures": [ | |
| "CoEncoderForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_co_encoder.CoEncoderConfig", | |
| "AutoModelForCausalLM": "modeling_co_encoder.CoEncoderForConditionalGeneration" | |
| }, | |
| "begin_of_context_token_id": 128002, | |
| "connector_hidden_act": "gelu", | |
| "context_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "Qwen/Qwen2-0.5B", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 151643, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 151643, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 24, | |
| "min_length": 0, | |
| "model_type": "qwen2", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 14, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sep_token_id": null, | |
| "sliding_window": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "context_feature_layer": -2, | |
| "context_feature_select_strategy": "default", | |
| "end_of_context_token_id": 128003, | |
| "ignore_index": -100, | |
| "model_type": "co_encoder", | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 131072, | |
| "model_type": "llama", | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 128256 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.0.dev0" | |
| } | |