8-bit-telugu-bert / config.json
saicharan8's picture
Upload quantized Telugu BERT model
0e227c0 verified
{
"_name_or_path": "kuppuluri/telugu_bertu",
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_hidden_states": true,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"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"
},
"torch_dtype": "float16",
"total_flos": 4760363129328537600,
"transformers_version": "4.41.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 32000
}