Back to all models
question-answering mask_token: [MASK]
Context
Query this model
馃敟 This model is currently loaded and running on the Inference API. 鈿狅笍 This model could not be loaded by the inference API. 鈿狅笍 This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

鈿★笍 Upgrade your account to access the Inference API

							$
							curl -X POST \
-H "Authorization: Bearer YOUR_ORG_OR_USER_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"question": "Where does she live?", "context": "She lives in Berlin."}' \
https://api-inference.huggingface.co/models/ahotrod/albert_xxlargev1_squad2_512
Share Copied link to clipboard

Monthly model downloads

ahotrod/albert_xxlargev1_squad2_512 ahotrod/albert_xxlargev1_squad2_512
5,731 downloads
last 30 days

pytorch

tf

Contributed by

ahotrod DNeff
4 models

How to use this model directly from the 馃/transformers library:

			
Copy to clipboard
from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("ahotrod/albert_xxlargev1_squad2_512") model = AutoModelForQuestionAnswering.from_pretrained("ahotrod/albert_xxlargev1_squad2_512")

Albert xxlarge version 1 language model fine-tuned on SQuAD2.0

(updated 30Sept2020) with the following results:

exact: 86.11134506864315
f1: 89.35371214945009
total': 11873
HasAns_exact': 83.56950067476383
HasAns_f1': 90.06353312254078
HasAns_total': 5928
NoAns_exact': 88.64592094196804
NoAns_f1': 88.64592094196804
NoAns_total': 5945
best_exact': 86.11134506864315
best_exact_thresh': 0.0
best_f1': 89.35371214944985
best_f1_thresh': 0.0

from script:

python ${EXAMPLES}/run_squad.py \
  --model_type albert \
  --model_name_or_path albert-xxlarge-v1 \
  --do_train \
  --do_eval \
  --train_file ${SQUAD}/train-v2.0.json \
  --predict_file ${SQUAD}/dev-v2.0.json \
  --version_2_with_negative \
  --do_lower_case \
  --num_train_epochs 3 \
  --max_steps 8144 \
  --warmup_steps 814 \
  --learning_rate 3e-5 \
  --max_seq_length 512 \
  --doc_stride 128 \
  --per_gpu_train_batch_size 6 \
  --gradient_accumulation_steps 8 \
  --per_gpu_eval_batch_size 48 \
  --fp16 \
  --fp16_opt_level O1 \
  --threads 12 \
  --logging_steps 50 \
  --save_steps 3000 \
  --overwrite_output_dir \
  --output_dir ${MODEL_PATH}

using the following software & system:

Transformers: 3.1.0
PyTorch: 1.6.0
TensorFlow: 2.3.1
Python: 3.8.1
OS: Linux-5.4.0-48-generic-x86_64-with-glibc2.10
CPU/GPU: Intel i9-9900K / NVIDIA Titan RTX 24GB