| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "capsule_attention_gate_mode": "off", |
| "capsule_fusion_mode": "upper_only", |
| "capsule_last_layer_module": "none", |
| "capsule_llopa_enabled": true, |
| "capsule_lower_layers": 20, |
| "capsule_no_upper_attn": false, |
| "capsule_num_suffix_specials": 0, |
| "capsule_prefill_attn": "causal", |
| "capsule_prefill_mode": "lower", |
| "capsule_replay_module": "none", |
| "capsule_replay_per_layers": -1, |
| "capsule_system_prefill": "no_system", |
| "capsule_user_prefill": "full", |
| "eos_token_id": 128001, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 8.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "llama3" |
| }, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.55.0", |
| "use_cache": true, |
| "vocab_size": 128256, |
| "auto_map": { |
| "AutoModelForCausalLM": "modeling_llopa.LLOPAForCausalLM" |
| }, |
| "llopa_num_specials": 0 |
| } |
