| { | |
| "architectures": [ | |
| "YingLong" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "model_config.YingLongConfig", | |
| "AutoModelForCausalLM": "model.GPT" | |
| }, | |
| "_mlp_class": "LLaMAMLP", | |
| "_norm_class": "FusedRMSNorm", | |
| "bias": false, | |
| "block_size": 8224, | |
| "condense_ratio": 1, | |
| "haar_trans": true, | |
| "haar_trans_inv": true, | |
| "haar_trans_norm": "backward", | |
| "intermediate_size": 3072, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_layer": 12, | |
| "n_query_groups": 4, | |
| "norm_eps": 1e-05, | |
| "org": "Alibaba", | |
| "parallel_residual": false, | |
| "patch_size": 32, | |
| "quantitle": true, | |
| "rope_base": 10000, | |
| "rotary_percentage": 1.0, | |
| "shared_attention_norm": false, | |
| "unet": true, | |
| "vocab_size": 1 | |
| } |