ViperEkura

ViperEkura pushed to main at ViperEkura/AstrAI

2026-07-04 15:46:56 +08:00

8999ca89b8 feat: add JSONL dataset store with on-the-fly tokenization

1adca39cd8 fix: handle long sequences and optimize IFD computation

204873fa2f fix: handle long sequences and optimize IFD computation

a5c1de6b1b feat: add model_path temperature top_p top_k max_tokens system_prompt args to stream_chat

27524ad085 fix: reset sampler iter at epoch end so progress bar shows total after first epoch

Compare 15 commits »

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-28 16:57:49 +08:00

73cb02f0aa fix training hyperparams to match pretraining script: lr 1.5e-4, wd 0.1, warmup 0.02

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-28 16:52:20 +08:00

adc284920a add Alembic SFT data cleaning section with MinHash algorithm and fix bibliography order

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-28 15:50:07 +08:00

13089b002a fix training config: grad_accum 32, remove unused validation & activation ckpt

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-28 14:36:18 +08:00

d3fbe0ecc6 refactor: numerical stability analysis with residual scaling comparison

ViperEkura pushed to main at ViperEkura/AstrAI

2026-06-27 16:12:33 +08:00

6715461a36 chore : 升级 torch 2.11.0+cu128，移除自定义 Muon，修复 gloo device_id

ViperEkura pushed to main at ViperEkura/AstrAI

2026-06-25 17:22:45 +08:00

b4587c5d08 refactor : metric_logger 改用事件类型 (type=step/validation/epoch)

88ec63121d feat : GPT-2 residual scaling weight init

01d2da2893 feat : 训练支持 --schedule_type 及对应调度器参数

25d4ea3f91 refactor : 压缩测试代码，消除重复

39985840c7 refactor : neftune_alpha 在 Embedding 构造时传入，由模型配置链路负责

Compare 7 commits »

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-25 16:53:35 +08:00

3db1096c78 fix: add caption package, fix overfull hbox, correct RoFormer author names

ViperEkura created branch master in ViperEkura/AstrAI-paper

2026-06-25 15:51:14 +08:00

ViperEkura pushed to master at ViperEkura/AstrAI-paper

2026-06-25 15:51:14 +08:00

6f9278b35b Initial commit: BF16 weight lock-in paper for 1.2B Transformer training with AstrAI

ViperEkura created repository ViperEkura/AstrAI-paper

2026-06-25 15:49:38 +08:00

ViperEkura pushed to main at ViperEkura/postgraduate-prep

2026-06-20 18:11:54 +08:00

2586583e0e feat: 新增重积分章节（笔记+错题）

ViperEkura pushed to main at ViperEkura/AstrAI

2026-06-19 13:54:20 +08:00

8ab7564d02 docs: 重构 README 结构，全文档添加目录导航

d096b6e29e docs: 修复文档中过时的字段、签名和缺失的类

d88a41f8f1 fix: 修复预处理流水线 4 个致命问题

376e9eba80 feat: IFEval 使用 chat template 格式化 prompt，添加 model.eval()

a62c2e11a2 feat: IFD 默认使用 chat template，支持裸文本模式

Compare 8 commits »

ViperEkura pushed to main at ViperEkura/AstrAI

2026-06-16 22:34:33 +08:00

a30e3d5114 fix: 修复 shields.io GitHub badge 因 token 耗尽而无法显示

1818d06576 feat: 新增 IFD 数据质量评分工具, 移动 ppl 至 eval

4e8d1ee24e feat: 新增 IFEval 指令遵循评测

fec376b0dd fix : 修复策略相关文件的类型注解与抽象方法体

a2512f8a5a fix : resume_dir 无权重文件时不强制加载，支持仅配置训练

Compare 15 commits »

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-15 14:05:34 +08:00

b399d94de3 fix: add tokenizer thread-safety patch and disable frontend multiprocessing for image support

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-15 14:02:07 +08:00

3a3d0e2723 add modalities config for Qwen3-VL-8B-Instruct to enable image input

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-15 14:01:12 +08:00

9cbc7b0878 switch to Qwen3-VL-8B-Instruct, fix start.sh arg, enable tool calling with hermes parser

917ff1c357 refactor server.py to use vLLM Python API and add permission config

Compare 2 commits »

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-14 19:21:50 +08:00

b4490f26e2 update README with Qwen2.5 and manual start

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-14 19:21:31 +08:00

fe997f6522 log to project dir, add web.log to gitignore

ViperEkura pushed to main at ViperEkura/ToolAgent

2026-06-14 19:15:38 +08:00

45adc385a0 fix: use model defaults for Qwen2.5, hermes parser