| { | |
| "_name_or_path": "/mnt/bn/ridger1/flame/configs/GatedDeltaNet/gated_deltanet_340M_6.json", | |
| "architectures": [ | |
| "GatedDeltaNetForCausalLM" | |
| ], | |
| "attn": { | |
| "layers": [ | |
| 6, | |
| 11, | |
| 17, | |
| 23 | |
| ], | |
| "num_heads": 32, | |
| "num_kv_heads": 8, | |
| "qkv_bias": false, | |
| "rope_theta": 10000.0, | |
| "window_size": null | |
| }, | |
| "attn_mode": "chunk", | |
| "bos_token_id": 1, | |
| "conv_size": 4, | |
| "eos_token_id": 2, | |
| "expand_k": 1, | |
| "expand_v": 1, | |
| "fuse_cross_entropy": true, | |
| "fuse_norm": true, | |
| "fuse_swiglu": true, | |
| "head_dim": 256, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gated_deltanet", | |
| "norm_eps": 1e-06, | |
| "norm_first": false, | |
| "num_heads": 4, | |
| "num_hidden_layers": 24, | |
| "qk_activation": "silu", | |
| "qk_norm": "l2", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0", | |
| "use_beta": true, | |
| "use_cache": true, | |
| "use_gate": true, | |
| "use_output_norm": true, | |
| "use_short_conv": true, | |
| "vocab_size": 32000 | |
| } | |