config.json

{
  "_name_or_path": "bigscience/bloom-1b7",
  "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": 2048,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "masked_softmax_fusion": true,
  "model_type": "bloom",
  "n_head": 16,
  "n_inner": null,
  "n_layer": 24,
  "offset_alibi": 100,
  "pad_token_id": 3,
  "pretraining_tp": 2,
  "quantization_config": {
    "batch_size": 1,
    "bits": 8,
    "block_name_to_quantize": null,
    "cache_block_outputs": true,
    "damp_percent": 0.1,
    "dataset": "wikitext2",
    "desc_act": false,
    "exllama_config": {
      "version": 1
    },
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "modules_in_block_to_quantize": null,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false,
    "use_exllama": true
  },
  "seq_length": 4096,
  "skip_bias_add": true,
  "skip_bias_add_qkv": false,
  "slow_but_exact": false,
  "torch_dtype": "float16",
  "transformers_version": "4.41.2",
  "unk_token_id": 0,
  "use_cache": true,
  "vocab_size": 250880
}