| { | |
| "architectures": [ | |
| "PaTHAttentionForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "elementwise_affine": true, | |
| "eos_token_id": 2, | |
| "fuse_cross_entropy": true, | |
| "fuse_linear_cross_entropy": false, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "model_type": "path_attn", | |
| "norm_eps": 1e-06, | |
| "num_heads": 16, | |
| "num_hidden_layers": 22, | |
| "num_kv_heads": 16, | |
| "qk_norm": false, | |
| "qkv_bias": false, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.4", | |
| "use_cache": true, | |
| "use_forget_gate": false, | |
| "use_l2warp": false, | |
| "use_low_rank_w": true, | |
| "use_w_shortconv": true, | |
| "vocab_size": 32000 | |
| } | |