| { |
| "_name_or_path": "configs/hgrn_s90_340M.json", |
| "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, |
| "num_heads": 1, |
| "num_hidden_layers": 24, |
| "prune_linear": true, |
| "prune_mlp": true, |
| "pruning_end_step": 10240, |
| "pruning_frequency": 256, |
| "pruning_start_step": 2049, |
| "target_sparsity": 0.9, |
| "tie_word_embeddings": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.49.0", |
| "use_cache": true, |
| "use_lower_bound": true, |
| "use_pruning": true, |
| "use_short_conv": false, |
| "vocab_size": 32000 |
| } |
|
|
