| { | |
| "vocab_size": 49152, | |
| "max_seq_len": 8192, | |
| "d_model": 384, | |
| "n_layers": 32, | |
| "n_heads": 6, | |
| "ffn_hidden_dim": 1024, | |
| "rope_theta": 10000.0, | |
| "rms_norm_eps": 1e-05, | |
| "initializer_range": 0.02, | |
| "dropout": 0.0, | |
| "tie_word_embeddings": true, | |
| "bias": false, | |
| "pad_token_id": 0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "unk_token_id": 3, | |
| "model_type": "qed", | |
| "architectures": [ | |
| "QEDForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_qed.QEDConfig", | |
| "AutoModelForCausalLM": "modeling_qed.QEDForCausalLM" | |
| }, | |
| "onnx": { | |
| "quantized": true | |
| } | |
| } |