config.json

{
  "_name_or_path": "DeepXR/Helion-2.5-Rnd",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "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,
    "original_max_position_embeddings": 16384,
    "type": "yarn"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "vocab_size": 128256,
  "pad_token_id": 128001,
  "mlp_bias": false,
  "head_dim": 128,
  "attention_implementation": "flash_attention_2",
  "use_sliding_window": false,
  "sliding_window": null,
  "quantization_config": {},
  "safetensors": {
    "enabled": true,
    "total_shards": 83,
    "shard_pattern": "shard_{:02d}.safetensors",
    "shard_range": "shard_00 to shard_82",
    "index_file": "model.safetensors.index.json",
    "shard_size_gb": 1.69,
    "shard_size_gib": 1.57,
    "fast_loading": true,
    "zero_copy": true
  },
  "optimization": {
    "flash_attention": true,
    "gradient_checkpointing": false,
    "tensor_parallel_size": 2,
    "pipeline_parallel_size": 1,
    "gpu_memory_fraction": 0.95,
    "max_batch_size": 32
  },
  "auto_map": {
    "AutoConfig": "configuration_llama.LlamaConfig",
    "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM"
  }
}