neuron_config.json

{
  "_attn_implementation_autoset": false,
  "_name_or_path": "meta-llama/Llama-3.1-8B",
  "add_cross_attention": false,
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attribute_map": {},
  "bad_words_ids": null,
  "begin_suppress_tokens": null,
  "bos_token_id": 128000,
  "chunk_size_feed_forward": 0,
  "cross_attention_hidden_size": null,
  "decoder_start_token_id": null,
  "diversity_penalty": 0.0,
  "do_sample": false,
  "early_stopping": false,
  "encoder_no_repeat_ngram_size": 0,
  "eos_token_id": 128001,
  "exponential_decay_length_penalty": null,
  "finetuning_task": null,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "fused_spec_config": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "is_decoder": false,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "length_penalty": 1.0,
  "max_length": 20,
  "max_position_embeddings": 131072,
  "min_length": 0,
  "mlp_bias": false,
  "model_type": "llama",
  "neuron_config": {
    "activation_quantization_type": null,
    "allow_input_truncation": false,
    "async_mode": false,
    "attn_cls": "NeuronLlamaAttention",
    "attn_kernel_enabled": false,
    "batch_size": 32,
    "bucket_n_active_tokens": false,
    "buckets": [
      16000
    ],
    "cc_pipeline_tiling_factor": 2,
    "context_encoding_buckets": null,
    "cp_max_num_seqs": 0,
    "cp_num_active_blocks": 0,
    "ctx_batch_size": 1,
    "draft_model_modules_to_not_convert": null,
    "enable_bucketing": true,
    "enable_eagle_draft_input_norm": false,
    "enable_eagle_speculation": false,
    "enable_fused_speculation": false,
    "enable_token_tree": false,
    "ep_degree": 1,
    "flash_decoding_enabled": false,
    "fused_qkv": false,
    "is_block_kv_layout": false,
    "is_chunked_prefill": false,
    "is_continuous_batching": true,
    "is_eagle_draft": false,
    "is_medusa": false,
    "is_prefill_stage": null,
    "is_prefix_caching": false,
    "kv_cache_batch_size": 32,
    "kv_cache_padding_size": 0,
    "kv_cache_quant": false,
    "kv_cache_tiling": false,
    "local_ranks_size": 16,
    "logical_nc_config": 1,
    "lora_config": null,
    "max_batch_size": 32,
    "max_context_length": 16000,
    "max_length": 16000,
    "max_new_tokens": null,
    "medusa_speculation_length": 0,
    "medusa_tree": null,
    "mlp_kernel_enabled": false,
    "mlp_kernel_fuse_residual_add": false,
    "modules_to_not_convert": null,
    "n_active_tokens": 16000,
    "n_positions": 16000,
    "num_medusa_heads": 0,
    "on_cpu": false,
    "on_device_sampling_config": {
      "deterministic": false,
      "do_sample": false,
      "dynamic": true,
      "global_topk": 256,
      "on_device_sampling_config": true,
      "temperature": 1.0,
      "top_k": 1,
      "top_p": 1.0
    },
    "output_logits": false,
    "overrides_torch_dtype": true,
    "pa_block_size": 16000,
    "pa_num_blocks": 32,
    "padding_side": "right",
    "pp_degree": 1,
    "qk_layernorm": false,
    "qkv_kernel_enabled": false,
    "qkv_kernel_nbsd_layout": false,
    "quantization_dtype": "int8",
    "quantization_type": "per_tensor_symmetric",
    "quantize_clamp_bound": Infinity,
    "quantized": false,
    "quantized_checkpoints_path": null,
    "quantized_mlp_kernel_enabled": false,
    "rmsnorm_quantize_kernel_enabled": false,
    "rpl_reduce_dtype": "bfloat16",
    "save_sharded_checkpoint": true,
    "seq_len": 16000,
    "sequence_parallel_enabled": false,
    "skip_sharding": false,
    "skip_warmup": true,
    "spec_batch_size": 32,
    "speculation_length": 0,
    "start_rank_id": 0,
    "target": null,
    "tkg_batch_size": 32,
    "token_generation_buckets": null,
    "token_tree_config": null,
    "torch_dtype": "bfloat16",
    "tp_degree": 16,
    "vocab_parallel": false,
    "weights_to_skip_layout_optimization": [],
    "world_size": 16
  },
  "no_repeat_ngram_size": 0,
  "num_attention_heads": 32,
  "num_beam_groups": 1,
  "num_beams": 1,
  "num_cores_per_group": 1,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_scores": false,
  "pad_token_id": null,
  "prefix": null,
  "pretraining_tp": 1,
  "problem_type": null,
  "pruned_heads": {},
  "remove_invalid_values": false,
  "repetition_penalty": 1.0,
  "return_dict": true,
  "return_dict_in_generate": false,
  "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,
  "sep_token_id": null,
  "suppress_tokens": null,
  "task_specific_params": null,
  "temperature": 1.0,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": false,
  "tokenizer_class": null,
  "top_k": 50,
  "top_p": 1.0,
  "torchscript": false,
  "transformers_version": "4.51.3",
  "typical_p": 1.0,
  "use_bfloat16": false,
  "use_cache": true,
  "vocab_size": 128256
}