| { | |
| "architectures": [ | |
| "ARLoopForCausalLM" | |
| ], | |
| "attnres_block_size": 24, | |
| "auto_map": { | |
| "AutoConfig": "configuration_arloop.ARLoopConfig", | |
| "AutoModelForCausalLM": "modeling_arloop.ARLoopForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "embedding_scale": 1.0, | |
| "eos_token_id": 0, | |
| "head_dim": 128, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "logit_softcap": null, | |
| "loop_count": 3, | |
| "max_position_embeddings": 4096, | |
| "model_type": "arloop", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 72, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "physical_layers": 24, | |
| "qk_norm": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_condense_ratio": 1, | |
| "rope_theta": 50000, | |
| "sw_blocks": 3, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.12.1", | |
| "use_cache": true, | |
| "vocab_size": 49152, | |
| "torch_dtype": "bfloat16" | |
| } | |