Commit Graph

29 Commits

Author SHA1 Message Date
8803fc8859 Update README.md 2025-04-17 23:26:03 +00:00
cf02bf025c Update README.md 2025-04-17 23:25:40 +00:00
Josephine Parquet
f499ead74c
Update README.md 2024-07-10 11:59:18 +00:00
Josephine Parquet
4b27fa32bf
Rename LICENSE to LICENSE.md 2024-07-10 11:58:16 +00:00
Jonathan Tow
8879812ccc
tmpfix(tokenizer_config): force GPT2TokenizerFast 2024-06-05 19:45:00 +00:00
Hassan Zayour
78f86b80f0
Update README.md 2024-04-12 08:21:42 +00:00
Jonathan Tow
3a8f08d8ab
Update README.md 2024-04-08 20:18:37 +00:00
Jonathan Tow
16f78806b1
Update README.md 2024-04-08 19:30:37 +00:00
Jonathan Tow
33923f685b
fix(README): correct tokenizer name 2024-03-21 22:01:19 +00:00
Jonathan Tow
db5a120c4d
fix(README): remove trust_remote_code requirement from tokenizer snippet 2024-03-01 07:35:30 +00:00
Jonathan Tow
a7a1fb8a83
update(tokenizer): convert to GPT2Tokenizer (#7)
- update(tokenizer): convert to `GPT2Tokenizer` (85625532dc8753c206eecc8a76323783a7b64744)
2024-03-01 07:31:02 +00:00
Jonathan Tow
a2eb1af48d
revert(config): use float16 default torch dtype 2024-02-21 20:41:28 +00:00
Jonathan Tow
ebf5f386bd
merge: upload transformers implementation (#6)
- merge: upload `transformers` implementation (efd6eabee32eabd8675eae49359287ad061fe197)
- feat: use latest modeling code (163f149452b3ecef0f4c3df5ce63c69652e45b78)
2024-02-21 19:52:05 +00:00
Marco Bellagente
39d1453f64
Update README.md 2024-02-15 08:39:21 +00:00
Jonathan Tow
39849ba308
feat: add initial tech report 2024-02-15 04:58:48 +00:00
Jonathan Tow
64c3d6a37d
fix(README): clarify usage of bias terms 2024-02-01 23:55:19 +00:00
Jonathan Tow
1909ae19b3
fix(modeling): use correct base_model_prefix name 2024-01-29 19:49:03 +00:00
Jonathan Tow
21ee10d32c
fix(tokenizer): expose errors 2024-01-25 16:17:34 +00:00
jon-tow
810b45c00e feat: add dropout support 2024-01-23 18:49:25 +00:00
jon-tow
4c846d7114 fix: make eos_token/pad_token overridable and add pickle support 2024-01-22 23:45:51 -05:00
Jonathan Tow
720763ede4
update(README): add extra lang tags 2024-01-20 18:32:37 +00:00
Jonathan Tow
9f2def929c
fix: add default special tokens 2024-01-19 22:54:48 +00:00
Jonathan Tow
ca32832c44
fix: add default special tokens 2024-01-19 22:52:04 +00:00
Jonathan Tow
192936bf86
fix: revert zephyr tokenizer config change 2024-01-19 22:43:56 +00:00
Max
507254d7bd
fix: add chat template to tokenizer config 2024-01-19 22:01:18 +00:00
jon-tow
e6185e1580 feat: add LICENSE 2024-01-19 14:11:14 -05:00
Jonathan Tow
a8f2f2862b
feat(tokenizer): expose merge ranks and special tokens for GGUF 2024-01-19 18:22:13 +00:00
jon-tow
3aeae29673 init: release 2024-01-18 23:46:52 +00:00
Jonathan Tow
a3cceb4c4c
initial commit 2024-01-18 15:49:16 +00:00