File size: 1,115 Bytes
6fbc738 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
{
"_name_or_path": "microsoft/BioGPT-Large-PubMedQA",
"activation_dropout": 0.0,
"architectures": [
"BioGptForCausalLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1600,
"initializer_range": 0.02,
"intermediate_size": 6400,
"layer_norm_eps": 1e-12,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "biogpt",
"num_attention_heads": 25,
"num_hidden_layers": 48,
"pad_token_id": 1,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"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": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"scale_embedding": true,
"torch_dtype": "float16",
"transformers_version": "4.38.0",
"use_cache": true,
"vocab_size": 57726
}
|