{ "architectures": [ "LlamaForCausalLM" ], "attention_axis_name": "sp", "attention_bias": false, "attention_dropout": 0.0, "attn_mechanism": "vanilla", "axis_dims": [ 1, 1, 1, -1 ], "axis_names": [ "dp", "fsdp", "tp", "sp" ], "backend": null, "bits": null, "block_b": 1, "block_k": 128, "block_q": 128, "bos_token_id": 128000, "easy_method": "train", "embd_pdrop": 0.0, "eos_token_id": [ 128001, 128008, 128009 ], "fcm_max_ratio": 0.0, "fcm_min_ratio": 0.0, "flash_attention_backward_pass_impl": "triton", "freq_max_position_embeddings": 32768, "gradient_checkpointing": "nothing_saveable", "hardware_abstraction": false, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "mask_max_position_embeddings": 32768, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "number_rep_kv": 1, "pallas_k_block_size": null, "pallas_m_block_size": null, "pallas_n_block_size": null, "partition_axis": [ [ "fsdp", "dp" ], "sp", "sp", "tp", "sp", "tp", null, null, null, null, "tp", "sp", null ], "platform": null, "pretraining_tp": 1, "quantize_kv_cache": false, "resid_pdrop": 0.0, "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": 10000.0, "scan_attention_layers": false, "scan_layers": true, "scan_mlp_chunk_size": 1024, "scan_ring_attention": true, "shard_attention_computation": true, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.46.2", "use_cache": true, "use_scan_mlp": false, "use_sharded_kv_caching": true, "use_sharding_constraint": false, "vocab_size": 128256 }