| { | |
| "architectures": [ | |
| "HATForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "config.HATArchitectureConfig", | |
| "AutoModelForCausalLM": "model.HATForCausalLM" | |
| }, | |
| "backbone_config": { | |
| "hidden_size": 8192, | |
| "intermediate_size": 28672, | |
| "is_neox_style": false, | |
| "key_query_norm": false, | |
| "key_query_norm_per_head": false, | |
| "max_position_embeddings": 12288, | |
| "mlp_bias": false, | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "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, | |
| "sliding_window": null, | |
| "transformers_version": null, | |
| "use_cache": true, | |
| "vocab_size": 0 | |
| }, | |
| "decoder_config": { | |
| "cross_attention_config": { | |
| "attention_num_kv_heads": 16, | |
| "hidden_size": 2048, | |
| "hidden_size_kv": 8192, | |
| "hidden_size_q": 2048, | |
| "key_query_norm": false, | |
| "key_query_norm_per_head": false, | |
| "num_attention_heads": 16, | |
| "word_window_size": 1 | |
| }, | |
| "cross_attn_every_layer": true, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "is_neox_style": false, | |
| "key_query_norm": false, | |
| "key_query_norm_per_head": false, | |
| "max_position_embeddings": 98304, | |
| "mlp_bias": false, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 100000, | |
| "sliding_window": 768, | |
| "transformers_version": null, | |
| "use_cache": true, | |
| "vocab_size": 256 | |
| }, | |
| "encoder_config": { | |
| "cross_attention_config": { | |
| "attention_num_kv_heads": 64, | |
| "hidden_size": 8192, | |
| "hidden_size_kv": 2048, | |
| "hidden_size_q": 8192, | |
| "key_query_norm": false, | |
| "key_query_norm_per_head": false, | |
| "num_attention_heads": 64, | |
| "word_window_size": 1 | |
| }, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "is_neox_style": false, | |
| "key_query_norm": false, | |
| "key_query_norm_per_head": false, | |
| "max_position_embeddings": 98304, | |
| "mlp_bias": false, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 100000, | |
| "sliding_window": 768, | |
| "transformers_version": null, | |
| "use_cache": true, | |
| "vocab_size": 256 | |
| }, | |
| "max_position_embeddings": 98304, | |
| "max_word_size": 100, | |
| "model_type": "hierarchical_autoregressive_transformer", | |
| "sliding_window": 768, | |
| "special_token_dict": { | |
| "<|begin_of_text|>": 250, | |
| "<|end_header_id|>": 252, | |
| "<|eot_id|>": 192, | |
| "<|start_header_id|>": 251 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3" | |
| } | |