Commit Graph

1641 Commits

Author SHA1 Message Date
hoshi-hiyouga
e12c80ace8 Merge pull request #6367 from hiyouga/hiyouga/add_model
[model&template] add llama3.3 & support llama3 tool prompt
2024-12-18 00:13:28 +08:00
hiyouga
b24ae55ebf support llama3 tool prompt 2024-12-17 15:52:37 +00:00
Yaser Afshar
1c8ad22a5f Add missing key to init_kwargs 2024-12-17 12:34:05 +00:00
Yaser Afshar
0943776326 Add trust_remote_code parameter and remove True
- Introduced a new model parameter `trust_remote_code`
- Set the default value of `trust_remote_code` to `False`
  to enhance security
2024-12-17 12:25:12 +00:00
hoshi-hiyouga
a665ad6178 Merge pull request #6364 from hiyouga/hiyouga/control_reenterent_gc
[model] support non-reenterent-gc
2024-12-17 19:58:36 +08:00
hiyouga
f319da6937 support non-reenterent-gc & fix #6358 2024-12-17 11:41:59 +00:00
hoshi-hiyouga
6973828307 Merge pull request #6363 from hiyouga/hiyouga/control_skip_eos
[infer] support control eos
2024-12-17 19:35:40 +08:00
hiyouga
eda76de32b support control eos, fix #6345 2024-12-17 10:42:05 +00:00
hiyouga
2d107d3aef generalized packing & fix #6343 2024-12-17 10:26:19 +00:00
hiyouga
142191e466 fix #6348 2024-12-17 10:06:46 +00:00
hiyouga
2811814fc4 fix mrope 2024-12-12 15:08:17 +00:00
hiyouga
99c62660c6 support qwen2vl train proj only 2024-12-05 10:37:42 +00:00
hiyouga
207f8b069c support qwen2vl vllm infer 2024-12-05 10:17:26 +00:00
hiyouga
eb3e147d19 fix scripts 2024-12-05 03:47:32 +00:00
hoshi-hiyouga
cf29846830 Merge pull request #6160 from village-way/pr_dataloader
fix:tokenized_path not None and load_from_disk return Dataset Trigger…
2024-12-04 22:18:19 +08:00
hoshi-hiyouga
6a5074e466 lint 2024-12-04 22:08:27 +08:00
hiyouga
1324d158f9 support batch infer in vllm 2024-12-04 13:50:00 +00:00
hoshi-hiyouga
263cb82bdb Merge pull request #6170 from hykilpikonna/main
[+] Show the hostname in webui title
2024-12-04 18:07:29 +08:00
hiyouga
dbb9e5b70e fix vlm zero3 training 2024-12-04 09:40:39 +00:00
Azalea
6554cdeedb [U] Compute hostname differently 2024-11-28 22:23:41 -05:00
hiyouga
68a612115a add qwq 2024-11-28 08:50:57 +00:00
Azalea
dfb953b1ad [+] Show the hostname 2024-11-28 12:25:02 +08:00
wangdepeng
4424d4de8a fix:tokenized_path not None and load_from_disk return Dataset Trigger stuck 2024-11-27 16:44:42 +08:00
hiyouga
046b6fb118 fix dataset 2024-11-27 06:27:44 +00:00
hiyouga
ec9ff8caa2 add skywork o1 2024-11-27 05:51:59 +00:00
hiyouga
17afb7d410 add marco-o1 and openo1 dataset 2024-11-27 04:20:23 +00:00
hoshi-hiyouga
b26c490ac3 Merge pull request #6152 from hiyouga/hiyouga/add_num_proc_in_data_load
[data] add num_proc in load_dataset
2024-11-27 00:16:15 +08:00
hiyouga
362d579ce8 fix #6149 2024-11-26 16:03:02 +00:00
hiyouga
598c22e43f fix mllama cross_mask 2024-11-26 15:56:58 +00:00
hoshi-hiyouga
da9e4ddd26 lint 2024-11-25 22:55:56 +08:00
hoshi-hiyouga
d87e16cf5c fix #6139 2024-11-25 22:22:06 +08:00
hoshi-hiyouga
75b586c31a fix visual patch 2024-11-25 20:06:06 +08:00
hoshi-hiyouga
0516e556a7 fix #6136 2024-11-25 19:43:42 +08:00
hiyouga
b0ccc2ee86 set dev version 2024-11-25 01:36:49 +08:00
hoshi-hiyouga
18daf10eda Merge pull request #6124 from hiyouga/hiyouga/release
[release] release v0.9.1
2024-11-25 00:20:02 +08:00
hoshi-hiyouga
07059a7ca4 Merge pull request #6126 from hiyouga/hiyouga/fix_vllm
[inference] fix vllm
2024-11-25 00:19:54 +08:00
hiyouga
13ee1f5cec fix vllm 2024-11-25 00:07:24 +08:00
hiyouga
8792d78c82 fix cli 2024-11-24 23:56:21 +08:00
hiyouga
d622f8fdec release v0.9.1 2024-11-24 23:48:41 +08:00
hiyouga
fa50fc470e fix qwen2vl vllm infer 2024-11-24 23:27:24 +08:00
hiyouga
df477370dc add forbidden modules 2024-11-23 18:34:15 +00:00
hiyouga
446441fdb0 fix inputs 2024-11-23 18:26:02 +00:00
marko1616
b1e43e56db Linter. 2024-11-23 16:09:04 +00:00
marko1616
8372c5e377 Tiny fix. 2024-11-23 16:09:01 +00:00
marko1616
3f2c056253 Support llama3.2vl. 2024-11-23 16:07:35 +00:00
hoshi-hiyouga
d20b97e7e9 do not split save_cmd ret value 2024-11-21 22:30:23 +08:00
superboy-zjc
aa6a174d68 [patch] Patch remote OS command injection vulnerability 2024-11-21 01:52:12 -05:00
hoshi-hiyouga
bd639a137e Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation
support effective tokens calculation on sft/dpo
2024-11-20 13:43:15 +08:00
Ting
40627c601e code refactor 2024-11-19 20:33:18 +08:00
Ting
f566ecc8d1 update 2024-11-19 19:12:10 +08:00