f5f75d8fa3
Merge d619d86c4c into dddedc6881
2026-05-11 04:19:16 +01:00
dddedc6881
[fix] repetition_penalty
2026-05-07 19:08:52 +08:00
802c15b2b4
[feat] reduce RL memory
2026-05-06 15:07:28 +08:00
e73a407f7a
Merge pull request #759 from TKiteRunner/fix/grpo-oom-reorder-rewards
...
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
2026-05-06 15:00:17 +08:00
10776417aa
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
2026-05-06 14:14:15 +08:00
5020dc9dd4
[update] readme
2026-05-06 13:41:46 +08:00
bdee223036
[fix] inference bug
2026-05-03 20:48:48 +08:00
06d882e4ef
[update] readme
2026-05-01 12:06:47 +08:00
da865af63d
[update] readme
2026-04-28 17:22:25 +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
d4c6bc5c7e
[update] readme
2026-04-27 10:59:41 +08:00
24896cd2c4
[update] readme
2026-04-24 20:16:06 +08:00
e2fc397176
[update] readme
2026-04-24 20:14:10 +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
693fb1ccf1
[update] readme
2026-04-21 14:34:46 +08:00
5416a44471
[fix] bugs
2026-04-21 13:03:34 +08:00
1718e9a44d
[fix] transformers-5.x
2026-04-19 23:48:54 +08:00
5704766352
[update] tie embedding
2026-04-19 21:57:28 +08:00
1ea113ea2c
[update] readme
2026-04-19 14:51:47 +08:00
487f78754d
[update] readme
2026-04-10 10:55:24 +08:00
e796b8028a
[fix] lora compile
2026-04-10 00:01:21 +08:00
b2488e6440
[update] readme
2026-04-09 19:00:41 +08:00
939dc8ff42
[update] readme
2026-04-09 18:54:17 +08:00
cadacabecb
[update] bench
2026-04-09 17:12:48 +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
25a7edcd6f
[update] image
2026-04-04 14:54:13 +08:00
cacf1d4cd0
[update] readme
2026-04-04 11:25:21 +08:00
2ab6455d9d
[update] open causal
2026-04-02 15:28:58 +08:00
9348fde743
[update] readme
2026-04-02 15:28:29 +08:00
90cd275524
[update] readme
2026-04-01 14:00:21 +08:00
b7e0ae21d6
[update] default model
2026-03-31 13:40:16 +08:00
b1865f75c2
[update] random seed
2026-03-27 21:20:02 +08:00
6b0b0c5e2f
[update] fp16 inference
2026-03-27 16:29:46 +08:00
88e675dc2c
[update] image
2026-03-26 15:35:42 +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
83e52f6a27
Merge pull request #698 from readlnh/master
...
[fix] 修复训练脚本中 1-indexed step 与 0-indexed 逻辑混用的问题
2026-03-24 13:41:20 +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
349e74ec7b
[update] empty_think_ratio
2026-02-06 19:15:21 +08:00
288e1ac02a
[update] empty_think_ratio
2026-02-06 01:36:02 +08:00
ccc190da05
[feat] data process
2026-02-06 01:17:57 +08:00
11a44340ba
[update] save interval
2026-01-30 20:30:50 +08:00
04616c41a5
[update] safe half
2026-01-30 20:29:31 +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
3a5aba82db
[fix] max length
2026-01-17 13:26:14 +08:00
714abcf802
[update] pretrain load
2026-01-17 12:00:17 +08:00
Sebastion
jingyaogong
TKiteRunner
jingyaogong
jingyaogong
readlnh