100apps
|
31b57a0569
|
Merge branch 'master' into master
|
2026-05-16 08:36:18 +08:00 |
jingyaogong
|
2b94dcb3d0
|
[update] num_workers=2
|
2026-05-12 09:54:46 +08:00 |
|
100apps
|
8b96a1efd9
|
fix(train): 解决Windows平台数据加载线程数问题
- 针对Windows系统默认将数据加载线程数设为0，避免多线程兼容性问题
- 保持其他平台默认线程数为8，优化数据加载性能
- 更新相关训练脚本train_pretrain_vlm.py和train_sft_vlm.py中的参数设置
- 修改.gitignore添加dataset目录防止数据误提交
- 在README中补充完整下载数据集的命令示例和说明
|
2026-05-11 23:43:45 +08:00 |
|
100apps
|
2c2f4b5161
|
remove minimind-3v
|
2026-05-11 23:31:40 +08:00 |
|
100apps
|
8b61e99080
|
chore(git): 更新.gitignore以忽略minimind-3v目录
- 在.gitignore文件末尾添加minimind-3v目录
- 避免将minimind-3v目录内容提交到版本控制系统
- 保持仓库整洁，防止不必要文件追踪
|
2026-05-11 23:30:46 +08:00 |
|
100apps
|
8fb354789b
|
chore(deps): 使用pyproject.toml和uv管理依赖环境
- 新增pyproject.toml文件，列出所有依赖及版本
- 移除旧的requirements.txt及相关内容
- 添加uv配置，支持不同平台的PyTorch索引
- 生成uv.lock文件，锁定依赖版本和来源
- 更新.gitignore，忽略虚拟环境和模型目录
- 修改README及README_en，指导使用uv同步和运行命令
- 将安装与运行示例均改为使用"uv run"和"uv sync"
- 适配模型下载与训练脚本调用方式使用uv工具
|
2026-05-11 23:28:03 +08:00 |
|
jingyaogong
|
ee18831dce
|
[fix] repetition_penalty
|
2026-05-07 19:08:14 +08:00 |
jingyaogong
|
b6a2532801
|
[update] readme
|
2026-05-02 00:35:40 +08:00 |
|
jingyaogong
|
1e86f201a2
|
[update] readme
|
2026-05-01 12:11:48 +08:00 |
|
jingyaogong
|
6fa6127b69
|
[update] readme
|
2026-04-28 17:26:02 +08:00 |
|
jingyaogong
|
0a9c06fa68
|
[update] readme
|
2026-04-27 10:57:35 +08:00 |
|
jingyaogong
|
fb38500054
|
[update] readme
|
2026-04-27 10:51:46 +08:00 |
|
jingyaogong
|
ff81f88833
|
[update] minimind-3v
|
2026-04-20 16:54:49 +08:00 |
|
jingyaogong
|
92ae3f963a
|
[update] readme
|
2026-04-20 00:06:27 +08:00 |
|
jingyaogong
|
9c3343dd88
|
[update] minimind-3v
|
2026-04-19 23:51:48 +08:00 |
|
jingyaogong
|
333654d6e9
|
[update] image
|
2026-04-04 14:57:45 +08:00 |
|
jingyaogong
|
f74124f6b9
|
[fix] bugs
|
2026-04-04 12:43:13 +08:00 |
|
jingyaogong
|
5098d67d9f
|
[fix] issue#114
|
2026-04-04 12:13:28 +08:00 |
jingyaogong
|
41c6d9e2a5
|
Merge pull request #115 from CgggggY/fix-single-batch-multi-image-shape
修复 bs=1 多图输入时 vision_tensors 维度不一致的问题
|
2026-04-04 12:06:04 +08:00 |
CgggggY
|
9e59a77080
|
Fix vision_tensors shape for bs=1 multi-image inputs
|
2026-04-04 11:32:38 +08:00 |
|
CgggggY
|
c840cdea35
|
Personal study notes for model_vlm (local only)
|
2026-04-04 11:22:27 +08:00 |
|
jingyaogong
|
4bc6524ac2
|
[fix] sync minimind
|
2026-04-02 16:34:38 +08:00 |
|
jingyaogong
|
887a42d9cb
|
[update] model
|
2026-04-02 15:29:50 +08:00 |
|
jingyaogong
|
28acd77d42
|
[fix] dummy grad
|
2026-04-01 17:56:44 +08:00 |
|
jingyaogong
|
48adb0fda0
|
[fix] pr113
|
2026-04-01 15:40:25 +08:00 |
|
jingyaogong
|
ac4c506eeb
|
Merge pull request #113 from JX446/master
fix: 修复 eval_vlm.py 中 f-string 引号嵌套导致的语法错误
|
2026-04-01 15:31:33 +08:00 |
DJY
|
eac29745da
|
fix: 修复 eval_vlm.py 中 f-string 引号嵌套导致的语法错误
- 修正第 66 行 print 语句中单双引号嵌套冲突的问题。
- 解决在部分 Python 版本下因反斜杠处理导致的 SyntaxError。
|
2026-04-01 15:11:38 +08:00 |
|
jingyaogong
|
14cfa88629
|
[update] requirement
|
2026-03-30 11:51:18 +08:00 |
|
jingyaogong
|
9089310ede
|
[update] fp16 inference
|
2026-03-27 16:22:47 +08:00 |
|
jingyaogong
|
1a6d650e9a
|
[update] readme
|
2026-03-26 11:46:05 +08:00 |
|
jingyaogong
|
e51dcf0fda
|
[update] minimind-3v
|
2026-03-26 00:09:02 +08:00 |
|
jingyaogong
|
56ab6ebd13
|
[update] readme
|
2026-02-05 00:23:20 +08:00 |
|
jingyaogong
|
33db76fe10
|
[update] dataset name
|
2026-02-05 00:22:58 +08:00 |
|
jingyaogong
|
b28715e6fd
|
[update] vlm params
|
2026-02-04 16:41:17 +08:00 |
|
jingyaogong
|
7e094afa59
|
[update] shuffle data
|
2026-01-18 17:02:24 +08:00 |
|
jingyaogong
|
326b24727e
|
[update] sync minimind
|
2026-01-15 21:51:58 +08:00 |
|
jingyaogong
|
d2bdff3269
|
[feat] test parquet
|
2025-12-27 10:56:07 +08:00 |
|
jingyaogong
|
fef284776f
|
[feat] delete images
|
2025-12-27 10:53:38 +08:00 |
|
jingyaogong
|
3684285a91
|
[feat] support parquet data
|
2025-12-27 10:49:50 +08:00 |
|
jingyaogong
|
1863743ee9
|
[feat] update readme
|
2025-12-27 10:48:54 +08:00 |
|
jingyaogong
|
32cf4c5c01
|
[fix] add gc
|
2025-12-27 01:09:33 +08:00 |
|
jingyaogong
|
b7cb98c136
|
[fix] reduce aux_loss_alpha
|
2025-12-05 23:07:55 +08:00 |
|
jingyaogong
|
13c3a2c093
|
[fix] cuda memory
|
2025-12-01 16:35:05 +08:00 |
|
jingyaogong
|
e03af46d12
|
[feat] update yarn
|
2025-12-01 16:34:00 +08:00 |
|
jingyaogong
|
a157b66ace
|
[feat] del cuda memory
|
2025-11-27 19:37:39 +08:00 |
|
jingyaogong
|
e613613a13
|
[feat] update model
|
2025-11-27 19:36:41 +08:00 |
|
jingyaogong
|
d698d98dc5
|
[feat] update readme
|
2025-11-11 11:12:09 +08:00 |
|
jingyaogong
|
92ca9959bb
|
[feat] update readme
|
2025-10-30 23:32:12 +08:00 |
|
jingyaogong
|
ca15b0440f
|
[feat] update readme
|
2025-10-30 23:31:19 +08:00 |
|
jingyaogong
|
2e548ba08e
|
[feat] update datasets
|
2025-10-30 11:08:30 +08:00 |