config.json

{
  "_name_or_path": "/tmp/tmpqcs22j25",
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "BloomForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_softmax_in_fp32": true,
  "bias_dropout_fusion": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_dropout": 0.0,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "masked_softmax_fusion": true,
  "model_type": "bloom",
  "n_head": 32,
  "n_inner": null,
  "n_layer": 30,
  "offset_alibi": 100,
  "pad_token_id": 3,
  "pretraining_tp": 4,
  "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"
  },
  "seq_length": 2048,
  "skip_bias_add": true,
  "skip_bias_add_qkv": false,
  "slow_but_exact": false,
  "torch_dtype": "float16",
  "transformers_version": "4.37.1",
  "unk_token_id": 0,
  "use_cache": true,
  "vocab_size": 250880
}