nbninh's picture
End of training
3c07192 verified
{
"_attn_implementation_autoset": true,
"_name_or_path": "bigscience/bloomz-560m",
"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": 1024,
"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": 1,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"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,
"quant_method": "bitsandbytes"
},
"seq_length": 2048,
"skip_bias_add": true,
"skip_bias_add_qkv": false,
"slow_but_exact": false,
"transformers_version": "4.46.0",
"unk_token_id": 0,
"use_cache": false,
"vocab_size": 250880
}