Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM
Python · active 2025-10-02 → 2026-06-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 263 days from 2025-10-02 to 2026-06-21. Pushes: 12 total, peak 3 in a day. Pull requests: 11 total, peak 3 in a day. Issues: 6 total, peak 2 in a day. Comments: 10 total, peak 3 in a day. Stars: 141 total, peak 5 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Geralt-Targaryen | 16 | 12 | 1 | 1 |
| bbkx226 | 6 | 0 | 3 | 3 |
| jingjin-dev | 4 | 0 | 2 | 2 |
| Amoshen | 3 | 0 | 1 | 2 |
| elvis-t9 | 2 | 0 | 0 | 0 |
| ClownW | 2 | 0 | 2 | 0 |
| feather820 | 2 | 0 | 0 | 0 |
| fluoryyn-art | 2 | 0 | 2 | 0 |
| harrison-huan-liu | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#45Geralt-Targaryen2026-04-09 07:49`config.json` broken for F2LLM-v2-80M and F2LLM-v2-330M — `max_window_layers` exceeds `num_hidden_layers`, causes `StrictDataclassClassValidationError` in transformers 5.x
- Pull request#44Geralt-Targaryen2026-03-05 06:52
- Issue#9Geralt-Targaryen2026-03-02 07:38[Codefuse开源轻训营] Support for gradient accumulation
- Issue#8Geralt-Targaryen2026-03-02 07:38[Codefuse开源轻训营] Support for Matryoshka Representation Learning (MRL) training strategy
- Issue#4feather8202025-12-25 08:44AttributeError: 'CodeFuseCGELargeConfig' object has no attribute 'rope_scaling'
- Issue#3feather8202025-12-25 08:43ValueError: The model class you are passing has a `config_class` attribute that is not consistent with the config class you passed (model has None and you passed <class 'transformers_modules.codefuse-ai.CodeFuse-CGE-Small.fd0871aa546be63188628752a09c4d42dd07250d.configuration_codefuse_cge_small.CodeFuseCGESmallConfig'>. Fix one of those so they match!
- Issue comment#42bbkx2262025-12-14 08:29Add Ray distributed training support and update requirements
- Pull request#40bbkx2262025-12-14 07:28
- Issue comment#39bbkx2262025-12-14 07:18Add Matryoshka Representation Learning (MRL) support and tests
- Issue comment#38bbkx2262025-12-14 07:07Add LoRA support and configuration to F2LLM
- Pull request#38bbkx2262025-12-14 07:05
- Pull request#37ClownW2025-12-13 15:04
- Pull request#36fluoryyn-art2025-12-13 09:35
- Pull request#35bbkx2262025-12-13 08:37
- Pull request#34fluoryyn-art2025-12-12 11:14
- Issue comment#32Amoshen2025-12-10 03:21Support for LoRA PEFT methods
- Issue comment#32Amoshen2025-12-10 03:20Support for LoRA PEFT methods
- Issue comment#29harrison-huan-liu2025-12-06 11:00Support for encoder-only models in the F2LLM framework
- Issue comment#27harrison-huan-liu2025-12-04 09:47Add LoRA Method Support for Parameter-Efficient Fine-Tuning
- Issue comment#23jingjin-dev2025-11-28 09:16lora-support
- Pull request#22jingjin-dev2025-11-28 08:40
- Pull request#20Amoshen2025-11-27 07:51
- Pull request#15ClownW2025-11-24 14:34
- Issue comment#12jingjin-dev2025-11-14 08:40encoder-only support pr
- Pull request#12jingjin-dev2025-11-14 08:39
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 141 stars here means stars gained during the window, not the repo's star count.