config.json

{
  "_name_or_path": "/tmp/tmp1xjh6nsb",
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "BloomForCausalLM"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "dtype": "float32",
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_dropout": 0.1,
  "hidden_size": 32,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "initializer_range": 0.02,
  "is_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "layer_norm_epsilon": 1e-05,
  "model_type": "bloom",
  "n_head": 4,
  "n_layer": 5,
  "n_positions": 512,
  "pad_token_id": 3,
  "pretraining_tp": 1,
  "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": 7,
  "slow_but_exact": true,
  "torch_dtype": "float16",
  "transformers_version": "4.37.1",
  "type_vocab_size": 16,
  "use_cache": true,
  "vocab_size": 1024
}