github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00
Code Issues Packages Projects Releases Wiki Activity

Remove albert-base-v2 since it fails torch_mlir.compile() (#644)

Browse Source
This commit is contained in:
Ean Garvey
2022-12-15 16:05:19 -06:00
committed by GitHub
parent e7e763551a
commit a14c53ad31
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tank/torch_model_list.csv
View File

@@ -1,6 +1,5 @@
model_name, use_tracing, model_type, dynamic, param_count, tags, notes
microsoft/MiniLM-L12-H384-uncased,True,hf,True,66M,"nlp;bert-variant;transformer-encoder","Large version has 12 layers; 384 hidden size; Smaller than BERTbase (66M params vs 109M params)"
albert-base-v2,True,hf,True,11M,"nlp;bert-variant;transformer-encoder","12 layers; 128 embedding dim; 768 hidden dim; 12 attention heads; Smaller than BERTbase (11M params vs 109M params); Uses weight sharing to reduce # params but computational cost is similar to BERT."
bert-base-uncased,True,hf,True,109M,"nlp;bert-variant;transformer-encoder","12 layers; 768 hidden; 12 attention heads"
bert-base-cased,True,hf,True,109M,"nlp;bert-variant;transformer-encoder","12 layers; 768 hidden; 12 attention heads"
google/mobilebert-uncased,True,hf,True,25M,"nlp,bert-variant,transformer-encoder,mobile","24 layers, 512 hidden size, 128 embedding"
1 model_name use_tracing model_type dynamic param_count tags notes
2 microsoft/MiniLM-L12-H384-uncased True hf True 66M nlp;bert-variant;transformer-encoder Large version has 12 layers; 384 hidden size; Smaller than BERTbase (66M params vs 109M params)
albert-base-v2 True hf True 11M nlp;bert-variant;transformer-encoder 12 layers; 128 embedding dim; 768 hidden dim; 12 attention heads; Smaller than BERTbase (11M params vs 109M params); Uses weight sharing to reduce # params but computational cost is similar to BERT.
3 bert-base-uncased True hf True 109M nlp;bert-variant;transformer-encoder 12 layers; 768 hidden; 12 attention heads
4 bert-base-cased True hf True 109M nlp;bert-variant;transformer-encoder 12 layers; 768 hidden; 12 attention heads
5 google/mobilebert-uncased True hf True 25M nlp,bert-variant,transformer-encoder,mobile 24 layers, 512 hidden size, 128 embedding