{ "_name_or_path": "/share/qhj/FlagEmbedding/research/Long_LLM/activation_beacon/data/outputs/beacon-qwen2.5-3B-full_coverage-interleave-2048_2048-8,16,32,64,128-step_random-qkv-redpajama/checkpoint-11432", "architectures": [ "Qwen2ForCausalLM" ], "auto_map": { "AutoConfig": "configuration_qwen2.Qwen2Config", "AutoModelForCausalLM": "modeling_qwen2.Qwen2ForCausalLM" }, "attention_dropout": 0.0, "beacon_attend_prev": true, "beacon_attn": "full-coverage", "beacon_embed_init": "eos", "beacon_parallel_window": 1, "beacon_param": [ "q", "k", "v" ], "beacon_pos": "interleave", "beacon_ratio": [ 8, 16, 32, 64, 128 ], "beacon_ratio_mix": "step-random", "beacon_sink_size": 0, "beacon_stride": 2048, "beacon_window": 2048, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.44.2", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }