{
  "_name_or_path": "/content/trained-model-1-merged-new",
  "alibi": true,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "RWForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_RW.RWConfig",
    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modelling_RW.RWForCausalLM"
  },
  "bias": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_dropout": 0.0,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "RefinedWebModel",
  "multi_query": false,
  "n_head": 32,
  "n_layer": 24,
  "parallel_attn": false,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "float32",
    "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
  },
  "torch_dtype": "float16",
  "transformers_version": "4.30.0.dev0",
  "use_cache": true,
  "vocab_size": 50304
}