f105f4cf20
Merge d619d86c4c into 4497610ec0
2026-05-23 17:19:14 +08:00
4497610ec0
[fix] issue#771
2026-05-19 17:40:03 +08:00
802c15b2b4
[feat] reduce RL memory
2026-05-06 15:07:28 +08:00
10776417aa
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
2026-05-06 14:14:15 +08:00
bdee223036
[fix] inference bug
2026-05-03 20:48:48 +08:00
773e451b11
[fix] bugs
2026-04-27 19:16:08 +08:00
6361510016
[fix] rollout bugs
2026-04-27 17:54:09 +08:00
d619d86c4c
fix: replace dangerous expression evaluation with AST-validated safe math parser (CWE-95)
...
Replace unconstrained expression evaluation in calculate_math tool
handlers with safe_eval_math(), which parses into an AST and only
allows literal numbers and basic arithmetic operators. Function calls,
attribute access, and name lookups are rejected, preventing arbitrary
code execution via prompt injection through LLM-generated tool calls.
Affected files:
- scripts/web_demo.py (Streamlit demo)
- scripts/eval_toolcall.py (tool call testing)
- trainer/train_agent.py (agent training)
2026-04-23 19:36:39 +01:00
5416a44471
[fix] bugs
2026-04-21 13:03:34 +08:00
e796b8028a
[fix] lora compile
2026-04-10 00:01:21 +08:00
5351424bf0
[fix] lora moe
2026-04-09 16:36:48 +08:00
aa3e6affa1
[update] add a comment
2026-04-09 15:09:58 +08:00
b8b3d35257
[update] change default seq_len
2026-03-26 10:09:06 +08:00
101d7df2da
[update] minimind-3
2026-03-25 23:57:45 +08:00
cf4b49a348
[fix] align log/save last-step check and ETA with 1-indexed step
2026-03-24 02:01:40 +01:00
d25500d363
[fix] gradient accumulation step alignment
2026-03-24 01:45:04 +01:00
11a44340ba
[update] save interval
2026-01-30 20:30:50 +08:00
fea69cf338
[fix] data skip
2026-01-18 16:56:29 +08:00
f7ffdf1fdb
[update] shuffle data
2026-01-18 16:39:34 +08:00
c090b69c4d
[update] align loss
2026-01-15 00:56:32 +08:00
e119db8478
[fix] compile unpack
2026-01-14 20:13:32 +08:00
81d24a4f16
[feat] add compile
2026-01-14 14:42:30 +08:00
df89069362
[update] params log
2026-01-07 23:08:45 +08:00
07364c3fbe
[update] rename train tokenizer
2026-01-06 01:17:33 +08:00
4e73f34823
[update] rename reason
2026-01-05 23:12:29 +08:00
42a4e8c86a
[fix] dist cleanup
2026-01-02 22:25:55 +08:00
9d898576ac
[update] aux loss
2026-01-01 22:41:46 +08:00
c65335b56f
[fix] experts unused
2025-12-31 21:47:04 +08:00
bc8fd82166
[fix] layers set 8
2025-12-31 21:06:37 +08:00
5dd4df7e18
[fix] moe unused
2025-12-31 21:00:06 +08:00
9236260a4a
[feat] get params
2025-12-31 20:46:59 +08:00
288a1d7212
[feat] get params
2025-12-31 20:44:34 +08:00
6242980917
[feat] update lr
2025-12-31 10:27:09 +08:00
7eae14f3ce
[feat] remove empty_cache
2025-12-27 07:14:36 +08:00
11b962da06
[feat] explicit left padding
2025-12-23 18:59:48 +08:00
fe24501602
[feat] adjust seq length
2025-12-14 20:41:58 +08:00
5129f0e2a2
[fix] dtype & lr
2025-12-09 13:01:38 +08:00
bf3878ace8
[fix] Refactor get_lr function to include min_lr calculation
...
这里的退火算法会让参数里的lr的起始值变成原来lr的1.1倍，作出如下修改
2025-12-06 17:09:51 +08:00
5e1447b913
[fix] cuda memory #559
2025-12-01 16:17:43 +08:00
6b86ea399a
[feat] release memory
2025-11-27 19:39:49 +08:00
d7f4f4eab8
[fix] ppo mask
2025-11-19 23:39:02 +08:00
9c98cabc9a
[fix] prompt length calculate
2025-11-15 18:25:37 +08:00
509d8dacf1
[feat] clear cache
2025-11-06 13:12:28 +08:00
0323815729
[feat] update import
2025-10-31 23:45:55 +08:00
bf123b585d
[feat] add args
2025-10-30 10:05:12 +08:00
1713c24114
[fix] model device
2025-10-29 10:36:28 +08:00
acd5925193
[feat] update trainer
2025-10-29 00:52:37 +08:00
8f7e07b8ef
[feat] update trainer
2025-10-28 23:30:10 +08:00
e8484874f5
[feat] pause-training
2025-10-26 18:49:52 +08:00
a82526da11
[feat] shuffle data
2025-10-23 20:13:28 +08:00
Sebastion
jingyaogong
TKiteRunner
jingyaogong
readlnh
dyhuachi