| { |
| "_name_or_path": "/data/fangxu/output/stage_1_gpt_chrono_unfreeze", |
| "architectures": [ |
| "Qwen2TSForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_qwen2.Qwen2TSConfig", |
| "AutoModel": "modeling_qwen2.Qwen2TSForCausalLM", |
| "AutoModelForCausalLM": "modeling_qwen2.Qwen2TSForCausalLM", |
| "AutoProcessor": "processing_qwen2_ts.Qwen2TSProcessor" |
| }, |
| "bos_token_id": 151643, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "ignore_index": -100, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "model_type": "qwen2", |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "pad_token_id": 151643, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 1000000.0, |
| "sliding_window": 131072, |
| "stage_2": true, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "train_from_scratch": true, |
| "transformers_version": "4.45.0", |
| "ts": { |
| "hidden_size": 3584, |
| "max_length": 2048, |
| "num_features": 2, |
| "num_layers": 2, |
| "patch_size": 32 |
| }, |
| "ts_config": { |
| "d_model": null, |
| "device": "cpu", |
| "model_kwargs": {}, |
| "model_name": "MOMENT", |
| "patch_len": 8, |
| "patch_stride_len": 8, |
| "seq_len": 512, |
| "t5_config": { |
| "architectures": [ |
| "T5ForConditionalGeneration" |
| ], |
| "d_ff": 2816, |
| "d_kv": 64, |
| "d_model": 1024, |
| "decoder_start_token_id": 0, |
| "dropout_rate": 0.1, |
| "eos_token_id": 1, |
| "feed_forward_proj": "gated-gelu", |
| "initializer_factor": 1.0, |
| "is_encoder_decoder": true, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "t5", |
| "n_positions": 512, |
| "num_decoder_layers": 24, |
| "num_heads": 16, |
| "num_layers": 24, |
| "output_past": true, |
| "pad_token_id": 0, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "vocab_size": 32128 |
| }, |
| "task_name": "reconstruction", |
| "transformer_backbone": "google/flan-t5-large", |
| "transformer_type": "encoder_only" |
| }, |
| "ts_path": "AutonLab/MOMENT-1-large", |
| "ts_token_end_index": 151666, |
| "ts_token_start_index": 151665, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|