{
  "_name_or_path": "fairseq-dense-125M",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "XGLMForCausalLM"
  ],
  "attention_dropout": 0.1,
  "attention_heads": 12,
  "bos_token_id": 50257,
  "d_model": 768,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "eos_token_id": 50259,
  "ffn_dim": 3072,
  "init_std": 0.02,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "xglm",
  "newlinemode": "s",
  "num_layers": 12,
  "pad_token_id": 1,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "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": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "scale_embedding": true,
  "tokenizer_class": "GPT2Tokenizer",
  "torch_dtype": "float16",
  "transformers_version": "4.39.3",
  "use_cache": true,
  "vocab_size": 50261
}