{
  "_name_or_path": "/data3/models/Molmo-72B-0924",
  "architectures": [
    "MolmoForCausalLM"
  ],
  "attention_layer_norm": false,
  "auto_map": {
    "AutoConfig": "config_molmo.MolmoConfig",
    "AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
  },
  "clip_qkv": null,
  "embedding_size": 152064,
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 59136,
  "layer_norm_eps": 1e-05,
  "layer_norm_type": "rms",
  "max_position_embeddings": 4096,
  "model_type": "molmo",
  "norm_after": false,
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "qkv_bias": true,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.4",
    "backend": "auto_round:gptq:exllamav2",
    "batch_size": 8,
    "bits": 4,
    "data_type": "int",
    "dataset": "NeelNanda/pile-10k",
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 1000,
    "low_gpu_mem_usage": true,
    "lr": 0.001,
    "minmax_lr": 0.001,
    "nsamples": 512,
    "quant_method": "intel/auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "to_quant_block_names": null
  },
  "rope_theta": 1000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "use_position_ids": true,
  "vocab_size": 152064,
  "weight_tying": false
}