| { | |
| "vocab_size": 8192, | |
| "d_model": 512, | |
| "num_heads": 8, | |
| "num_kv_heads": 4, | |
| "num_encoder_layers": 12, | |
| "num_decoder_layers": 8, | |
| "d_ff": 2048, | |
| "max_seq_len": 1024, | |
| "pad_token_id": 0, | |
| "eos_token_id": 1, | |
| "decoder_start_token_id": 1, | |
| "bos_token_id": 2, | |
| "unk_token_id": 3, | |
| "tool_call_token_id": 4, | |
| "tools_token_id": 5, | |
| "rope_theta": 10000.0, | |
| "rms_norm_eps": 1e-06, | |
| "dtype": "bfloat16", | |
| "activation": "swiglu", | |
| "num_memory_slots": 64, | |
| "dropout_rate": 0.1, | |
| "contrastive_dim": 128, | |
| "no_feedforward": true, | |
| "rope_keys_only": false | |
| } | |