config.json

{
  "_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": 20480,
  "hidden_size": 5120,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "output_projection": true,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "bits": 8,
    "fp8_static_quant": false,
    "group_size": 0,
    "kv_cache_quant_layers": [],
    "modules_to_not_convert": [
      "lm_head"
    ],
    "per_tensor": true,
    "quant_method": "sq",
    "zero_point": true
  },
  "torch_dtype": "float16",
  "transformers_version": "4.54.0",
  "use_cache": false,
  "vocab_size": 50272,
  "word_embed_proj_dim": 5120
}