140 Commits (main)

Author SHA1 Message Date
Brett Kuprel b785accffd update readme 2 years ago
Brett Kuprel 09a0f85b8e separate setup processes for flax and torch 2 years ago
Brett Kuprel b40fd83a0d mega works with latest flax version 0.5.2 now, removing 0.4.2 pin 2 years ago
Brett Kuprel eaee59a1ef update readme 2 years ago
Brett Kuprel f8bffc6892 update readme 2 years ago
Brett Kuprel 08b158d580 updated readme 2 years ago
Brett Kuprel d9d7f34b22 update readme 2 years ago
Brett Kuprel c8f3304363 update readme 2 years ago
Brett Kuprel b913b58353 pre converting params to torch allows mega to run in standard colab runtime 2 years ago
Brett Kuprel 41a44068d0 keep params in expendable mode 2 years ago
Brett Kuprel fb97ba5e20 update readme, cleanup 2 years ago
Brett Kuprel 005ee4938e
Update README.md 2 years ago
Brett Kuprel d99828a239 simplified flax attention and matched torch attention 2 years ago
Chenxi eb9f4c6b3b replicate demo 2 years ago
Brett Kuprel a4df279fd2 simplified attention and keys_values state resulted in decrease in inference time to 7.3 seconds (from ~10 seconds) 2 years ago
Brett Kuprel 764b5bbc0e works with latest flax version 0.5.2, updated requirements.txt 2 years ago
Brett Kuprel c4f613c89f readme wording 2 years ago
Brett Kuprel 6046863805 readme wording 2 years ago
Brett Kuprel 2b552fe9db readme wording 2 years ago
Brett Kuprel b7c2414c76 readme wording 2 years ago
Brett Kuprel 4e62f85ab9 readme wording 2 years ago
Brett Kuprel 53695e32f7 updated readme with torch examples 2 years ago
Brett Kuprel ed91ab4a30 refactored to load models once and run multiple times 2 years ago
Brett Kuprel 1fbb209623 fixed bug with cuda in detokenizer 2 years ago
Brett Kuprel aef24ea157 torch.no_grad(), cleanup 2 years ago
Omar Sanseviero efa40ab321
Update README.md 2 years ago
Brett Kuprel 6260252348 update readme 2 years ago
kuprel 2ad7009a16
Update README.md 2 years ago
Brett Kuprel 6a068651e5 updated colab 2 years ago
Brett Kuprel 24d8e29ef2 readme formatting 2 years ago
Brett Kuprel 8363495f0a updated readme 2 years ago
Brett Kuprel a014dccc05 fixed an issue with argument parser 2 years ago
Brett Kuprel e7001f063c simplified 2 years ago
Brett Kuprel 18e6a9852f license and cleanup 2 years ago
Brett Kuprel 32b7aa196b readme 2 years ago
Brett Kuprel 194ae7dfa1 examples 2 years ago
Brett Kuprel 97fe8515f1 first commit 2 years ago