config.json

{
  "_name_or_path": "/tmp/tmpp4mml04d",
  "_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": 10240,
  "hidden_size": 2560,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "torch_dtype": "float16",
  "transformers_version": "4.37.1",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 2560
}