config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_mechanism": "splash",
  "backend": null,
  "begin_suppress_tokens": [
    128000,
    128001
  ],
  "bits": null,
  "blocksize_b": 1,
  "blocksize_k": 128,
  "blocksize_q": 128,
  "bos_token_id": 128000,
  "decode_attn_mechanism": null,
  "decoder_start_token_id": 128000,
  "easy_method": "train",
  "embd_pdrop": 0.0,
  "eos_token_id": 128009,
  "fcm_max_ratio": -1,
  "fcm_min_ratio": -1,
  "flash_attention_backward_pass_impl": "triton",
  "freq_max_position_embeddings": 4096,
  "gradient_checkpointing": "nothing_saveable",
  "hardware_abstraction": false,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "kv_cache_quantization_blocksize": 64,
  "kv_cache_quantization_method": "None",
  "kv_cache_sharding_sequence_axis_name": "sp",
  "mask_max_position_embeddings": 4096,
  "max_position_embeddings": 4096,
  "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": 128,
  "pallas_m_block_size": 128,
  "pallas_n_block_size": 128,
  "partition_axis": {
    "attention_dim_axis": null,
    "attention_kv_dim_axis": null,
    "batch_axis": [
      "fsdp",
      "dp"
    ],
    "bias_head_sequence_axis": null,
    "bias_key_sequence_axis": null,
    "data_parallel_axis": "dp",
    "decode_attention_dim_axis": null,
    "decode_attention_kv_dim_axis": null,
    "decode_batch_axis": [
      "fsdp",
      "dp"
    ],
    "decode_head_axis": "tp",
    "decode_key_sequence_axis": "sp",
    "decode_kv_head_axis": "tp",
    "decode_query_sequence_axis": null,
    "expert_axis": "ep",
    "expert_gate_axis": null,
    "expert_parallel_axis": "ep",
    "fully_sharded_data_parallel_axis": "fsdp",
    "head_axis": "tp",
    "hidden_state_axis": "tp",
    "key_sequence_axis": "sp",
    "kv_head_axis": "tp",
    "mlp_intermediate_axis": "tp",
    "query_sequence_axis": "sp",
    "sequence_axis": "sp",
    "sequence_parallel_axis": "sp",
    "tensor_parallel_axis": "tp",
    "vocab_axis": "tp"
  },
  "platform": null,
  "precompute_masks": true,
  "pretraining_tp": 1,
  "quantization_blocksize": 64,
  "quantization_method": "None",
  "quantization_pattern": ".*",
  "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": 500000,
  "scan_attention_layers": false,
  "scan_layers": false,
  "scan_mlp_chunk_size": 1024,
  "scan_ring_attention": true,
  "sequence_axis_name": "sp",
  "shard_attention_computation": true,
  "sharding_axis_dims": [
    1,
    -1,
    1,
    1
  ],
  "sharding_axis_names": [
    "dp",
    "fsdp",
    "tp",
    "sp"
  ],
  "sharding_dcn_axis_dims": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_scan_mlp": false,
  "use_sharded_kv_caching": false,
  "use_sharding_constraint": false,
  "vocab_size": 128256
}