config.json

{
  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
  "architectures": ["LlamaForCausalLM"],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [128001, 128008, 128009],
  "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,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "use_cache": true,
  "vocab_size": 128256,
  "serverless": {
    "enabled": true,
    "max_batch_size": 64,                // Lowered batch size for better compatibility
    "max_sequence_length": 2048,
    "model_parallelism": {
      "enabled": true,
      "num_gpus": 1,
      "num_shards": 2                     // Adjusted for distributed inference
    },
    "quantization": {
      "enabled": true,
      "target_dtype": "int8"
    }
  }
}