| { | |
| "alpha_init_value": 0.5, | |
| "architectures": [ | |
| "HGRNForCausalLM" | |
| ], | |
| "attn": null, | |
| "attn_mode": "chunk", | |
| "bos_token_id": 1, | |
| "conv_size": 4, | |
| "elementwise_affine": true, | |
| "eos_token_id": 2, | |
| "expand_ratio": 1, | |
| "fuse_cross_entropy": true, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "max_position_embeddings": 2048, | |
| "model_type": "hgrn", | |
| "norm_eps": 1e-06, | |
| "norm_type": "rms_norm", | |
| "num_heads": 1, | |
| "num_hidden_layers": 24, | |
| "prune_linear": false, | |
| "prune_mlp": false, | |
| "pruning_end_step": 10000, | |
| "pruning_frequency": 500, | |
| "pruning_start_step": 1000, | |
| "target_sparsity": 0.8, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_lower_bound": true, | |
| "use_pruning": false, | |
| "use_short_conv": false, | |
| "vocab_size": 32000 | |
| } | |