bloom-1b7-8bit / config.json
rs224's picture
Upload BloomForTokenClassification (#1)
926d222
{
"_name_or_path": "bigscience/bloom-1b7",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"BloomForTokenClassification"
],
"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,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_11": 11,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"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": {
"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
},
"seq_length": 4096,
"skip_bias_add": true,
"skip_bias_add_qkv": false,
"slow_but_exact": false,
"torch_dtype": "float16",
"transformers_version": "4.30.0.dev0",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 250880
}