| { | |
| "architectures": [ | |
| "SDARForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_sdar.SDARConfig", | |
| "AutoModel": "modeling_sdar.SDARModel", | |
| "AutoModelForCausalLM": "modeling_sdar.SDARForCausalLM" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "flex_attention", | |
| "bos_token_id": 151643, | |
| "debug": false, | |
| "eos_token_id": 151643, | |
| "ep_size": 1, | |
| "fuse_cross_entropy": true, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "micro_forward": false, | |
| "model_type": "sdar", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "skip_checkpoint": false, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.4", | |
| "use_cache": false, | |
| "use_deepep": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |