| { | |
| "_name_or_path": "beacon-qwen-2-7b-instruct", | |
| "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": [ | |
| 2, | |
| 4, | |
| 8, | |
| 16, | |
| 32 | |
| ], | |
| "beacon_ratio_mix": "adapt-1024", | |
| "beacon_sink_size": 0, | |
| "beacon_stride": 2048, | |
| "beacon_window": 2048, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "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, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |