config.json

{
  "_name_or_path": "facebook/opt-125m",
  "_remove_final_layer_norm": false,
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "OPTForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "enable_bias": true,
  "eos_token_id": 2,
  "ffn_dim": 3072,
  "hidden_size": 768,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "batch_size": 1,
    "bits": 2,
    "block_name_to_quantize": "model.decoder.layers",
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "dataset": "c4",
    "desc_act": false,
    "disable_exllama": false,
    "exllama_config": {
      "version": 2
    },
    "exllama_version": 2,
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": 2048,
    "module_name_preceding_first_block": [
      "model.decoder.embed_tokens",
      "model.decoder.embed_positions",
      "model.decoder.final_layer_norm"
    ],
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "true_sequential": true,
    "use_cuda_fp16": true
  },
  "torch_dtype": "float16",
  "transformers_version": "4.36.0.dev0",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 768
}