github-featured/flagopen--flagembedding
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Commit Graph

  • d91e03c9bb deploy: fd1a2bdf69 gh-pages hanhainebula 2026-08-24 02:57:40 +00:00
  • fd1a2bdf69 Merge pull request #1596 from hanhainebula/master master v1.4.2 Jianlyu Chen 2026-08-24 10:54:09 +08:00
  • cdeb62a825 Bump package version to 1.4.2 hanhainebula 2026-08-24 10:53:07 +08:00
  • 3f8b44a76d Merge pull request #1595 from hanhainebula/master Jianlyu Chen 2026-08-24 10:48:44 +08:00
  • 71fa99750a Fix Transformers 5 tokenizer compatibility hanhainebula 2026-08-24 10:44:25 +08:00
  • 7b7be6748d Merge pull request #1594 from hanhainebula/master v1.4.1 Jianlyu Chen 2026-08-23 20:36:55 +08:00
  • 0752381a23 fix(reranker): normalize model mapping names hanhainebula 2026-08-23 20:35:16 +08:00
  • 807fc3fcc5 Merge pull request #1593 from hanhainebula/master Jianlyu Chen 2026-08-23 20:26:09 +08:00
  • 0e924f5205 fix(reranker): support transformers v5 tokenizer preparation hanhainebula 2026-08-23 20:17:50 +08:00
  • a26f9ef85f Merge pull request #1592 from hanhainebula/master Jianlyu Chen 2026-08-23 19:30:08 +08:00
  • 981dac2d8d Merge pull request #1580 from Gui-Yue/fix-transformers-v5-gemma-import Jianlyu Chen 2026-08-23 19:29:44 +08:00
  • 5894f91732 Fix Transformers 5 Trainer compatibility hanhainebula 2026-08-23 18:58:54 +08:00
  • 292ad785de Update README.md zhengliu 2026-08-14 14:16:02 +08:00
  • 92f5289505 Update README_zh.md zhengliu 2026-08-14 14:13:52 +08:00
  • b5a492d86c Fix Gemma reranker imports with Transformers v5 Gui-Yue 2026-05-19 00:05:59 +08:00
  • 7ed43d67ec Merge pull request #1575 from hanhainebula/master v1.4.0 Jianlyu Chen 2026-04-22 23:57:32 +08:00
  • a4247c6c99 chore: update version to 1.4.0 in setup.py Jianlv Chen 2026-04-22 23:56:53 +08:00
  • 8092277312 Merge pull request #1572 from lnxtree/master Jianlyu Chen 2026-04-22 23:13:06 +08:00
  • d82edd1ed1 fix: add DEFAULT_POOLING_METHOD to PseudoMoELLMEmbedder lnxtree 2026-04-02 22:06:41 +08:00
  • 0d27243941 test: Add examples of test scripts for pseudoMoE and coir pseudo-moe test entry lnxtree 2026-04-02 21:19:50 +08:00
  • ab7c252d62 feat(embedder): add decoder-only pseudo_moe inference with domain routing support - pass domain_for_pseudo_moe through evaluation runner to embedder initialization - add new decoder-only embedder implementation for pseudo MoE models lnxtree 2026-04-01 22:22:01 +08:00
  • d190647310 Merge pull request #1570 from lnxtree/master Jianlyu Chen 2026-04-01 10:32:52 +08:00
  • ac3e2390e0 feat: add use_mrl interface of finetune for embedder decode_only.icl and encoder_only.base lnxtree 2026-03-31 21:15:00 +08:00
  • 29d380b9e1 feat: add truncate_dim for evaluation and inference for embedder lnxtree 2026-03-31 17:10:51 +08:00
  • b09c37751d feat: add the 'use_mrl' interface to the finetune of embedder lnxtree 2026-03-31 15:35:31 +08:00
  • f17476f1b4 Merge pull request #1568 from lnxtree/feat-fix-embedder_use_bf16 Jianlyu Chen 2026-03-27 11:02:15 +08:00
  • 7e53f57f83 Merge branch 'FlagOpen:master' into feat-fix-embedder_use_bf16 lnxtree 2026-03-26 21:00:28 +08:00
  • 2ff964ee32 fix(eval): pass use_bf16 through AbsEvalRunner.get_model and COIR evaluator model initialization lnxtree 2026-03-26 20:59:03 +08:00
  • 4bcfc6e180 Merge pull request #1567 from lnxtree/feat-fix-embedder_use_bf16 Jianlyu Chen 2026-03-26 20:15:09 +08:00
  • 2955a5a6e5 fix(m3): make bf16 inference/train loading safe and unify numpy conversion - replace m3 embedder .cpu().numpy() paths with base _convert_to_numpy(...) for bf16-safe conversion - add torch_dtype plumbing in m3 runner model loading (AutoModel/colbert_linear/sparse_linear) to keep dtype behavior consistent lnxtree 2026-03-26 19:14:12 +08:00
  • d65ffb17b7 fix(embedder): add _convert_to_numpy in base class and guard bf16->numpy on non-cpu lnxtree 2026-03-26 15:19:05 +08:00
  • ac7a2747d3 Merge pull request #1566 from lnxtree/feat-fix-embedder_use_bf16 Jianlyu Chen 2026-03-26 14:32:19 +08:00
  • 19edba7b08 feat: fix the interface of attn_implementation in embedder.decode_only.*.load_model and reranker.decode_only.*.load_model lnxtree 2026-03-26 14:17:14 +08:00
  • 6679caaf65 fix: code format for inference.embedder.decoder_only.icl lnxtree 2026-03-26 14:00:41 +08:00
  • 5d6fa9a69e fix: add bf16 interface to EncoderOnlyEmbedderM3Runner.get_model lnxtree 2026-03-26 13:37:05 +08:00
  • 90957832ac feat(embedder): add use_bf16 support and unify inference dtype behavior add use_bf16 to auto embedder and all embedder constructors lnxtree 2026-03-26 12:17:14 +08:00
  • dbc600560b Merge pull request #1563 from therealmichaelberna/transformers-v5-compat Jianlyu Chen 2026-03-10 11:07:48 +08:00
  • 94993fd299 added init.py to fix import errors Michael Jay Berna 2026-03-09 18:12:33 +00:00
  • 3893bf2e4e feat: add compatibility with transformers V5 Michael Jay Berna 2026-03-05 14:48:52 +00:00
  • 6fd176266f Merge pull request #1553 from hanhainebula/master Jianlyu Chen 2025-12-15 16:51:06 +08:00
  • d166f499de add metric for evaluation: evaluate_recall_cap hanhainebula 2025-12-15 16:50:02 +08:00
  • bbc736f188 Merge pull request #1538 from hanhainebula/master Jianlyu Chen 2025-10-22 14:10:16 +08:00
  • 9e9cf5b37c fix bug: pytrec_eval installation issue hanhainebula 2025-10-22 14:09:47 +08:00
  • 90b12342b7 fix bug: pytrec_eval installation issue hanhainebula 2025-10-22 14:08:51 +08:00
  • f7cee83657 Merge pull request #1535 from hanhainebula/master Jianlyu Chen 2025-10-10 21:13:34 +08:00
  • 5a5dd621fa update examples README: support BRIGHT evaluation hanhainebula 2025-10-10 21:12:56 +08:00
  • 971236c869 Merge pull request #1534 from hanhainebula/master Jianlyu Chen 2025-10-10 20:21:24 +08:00
  • 545f0d7fab update examples README: support BRIGHT evaluation hanhainebula 2025-10-10 20:20:48 +08:00
  • a1befaa641 support evaluation: BRIGHT hanhainebula 2025-10-10 19:17:30 +08:00
  • 53240c5283 support evaluation: BRIGHT hanhainebula 2025-10-10 16:50:42 +08:00
  • c56fa29bc2 Merge pull request #1532 from hanhainebula/master Jianlyu Chen 2025-09-23 23:03:53 +08:00
  • 24bc8d15a6 fix bug: safe dist.get_rank() hanhainebula 2025-09-23 23:02:26 +08:00
  • 5e1f42f15c Merge pull request #1531 from hanhainebula/master Jianlyu Chen 2025-09-23 22:53:56 +08:00
  • ffea23c79d Update model_mapping for embedder inference - bge-code-v1, bge-reasoner-embed-qwen3-8b-0923 - Qwen3-Embedding-* hanhainebula 2025-09-23 22:51:11 +08:00
  • 8ca76af9f3 Update README of BGE-Reasoner - fix pony results of BGE-Reasoner-Embed-Qwen3-8B-0923 - add contact information hanhainebula 2025-09-23 22:41:24 +08:00
  • 9d5ae8ea65 Merge pull request #1528 from hanhainebula/master Jianlyu Chen 2025-09-23 02:41:24 +08:00
  • 1ee20581c3 Update BGE-Reasoner: Release v0923 embedder - BGE-Reasoner-Embed-Qwen3-8B-0923 hanhainebula 2025-09-23 02:39:38 +08:00
  • c6e49d74b0 Merge pull request #1527 from hanhainebula/master Jianlyu Chen 2025-09-22 20:36:12 +08:00
  • 17d8e8a566 fix abc/evaluation/runner.py: evaluate_metrics - when eval_results_path does not exist, continue hanhainebula 2025-09-22 20:35:28 +08:00
  • 7780cf3135 Merge pull request #1526 from hanhainebula/master Jianlyu Chen 2025-09-17 16:20:34 +08:00
  • f23392228a add use_fast_tokenizer param for finetuning - default: True hanhainebula 2025-09-17 16:18:53 +08:00
  • 6b0e34a48d Update BGE-Reasoner hanhainebula 2025-09-17 16:10:44 +08:00
  • 7bd64ce2e1 Merge pull request #1522 from hanhainebula/master Jianlyu Chen 2025-09-04 22:49:46 +08:00
  • da88e1eac0 Update BGE-Reasoner hanhainebula 2025-09-04 22:47:58 +08:00
  • 38f4bbf528 Merge pull request #1517 from hanhainebula/master Jianlyu Chen 2025-08-26 13:55:10 +08:00
  • de6a87713b Add Qwen3-Embedding-8B baseline for BGE-Reasoner hanhainebula 2025-08-26 13:49:06 +08:00
  • 0202aaad1f Merge pull request #1516 from hanhainebula/master Jianlyu Chen 2025-08-24 20:15:25 +08:00
  • 953f814204 Fix BGE-Reasoner Table & Results Sources hanhainebula 2025-08-24 20:07:10 +08:00
  • 21cbceae16 Fix BGE-Reasoner Table & Results Sources hanhainebula 2025-08-24 20:04:02 +08:00
  • 2225aacb54 Merge pull request #1514 from hanhainebula/master Jianlyu Chen 2025-08-19 22:54:58 +08:00
  • ba4a370d1b Update BGE-Reasoner: new SOTA on BRIGHT hanhainebula 2025-08-19 22:11:05 +08:00
  • 2ccec9ea70 Merge pull request #1512 from hanhainebula/master Jianlyu Chen 2025-08-14 15:25:43 +08:00
  • 9f8343f83c fix link in README of BGE-Reasoner hanhainebula 2025-08-14 15:24:48 +08:00
  • 41938fface Merge pull request #1511 from hanhainebula/master Jianlyu Chen 2025-08-14 13:58:38 +08:00
  • 14afc804b0 fix bold values in README of BGE-Reasoner hanhainebula 2025-08-14 13:57:43 +08:00
  • 47fbc70dde Merge pull request #1510 from hanhainebula/master Jianlyu Chen 2025-08-14 13:53:55 +08:00
  • 1408815f99 update README of BGE-Reasoner hanhainebula 2025-08-14 13:52:12 +08:00
  • 423a129fdc Release BGE-Reasoner-preview hanhainebula 2025-08-14 13:47:40 +08:00
  • b87a5685d5 Merge branch 'master' of github.com:hanhainebula/FlagEmbedding hanhainebula 2025-08-14 11:43:22 +08:00
  • 3bc1962480 fix bug: only modify vocab_size when necessary - when saving ckpt for decoder only embedder, check emb.pth hanhainebula 2025-07-15 10:33:52 +08:00
  • e22be56be6 Merge pull request #1492 from hanhainebula/master Jianlyu Chen 2025-07-13 00:49:19 +08:00
  • 90173852db disable warning info: train_group_size is None hanhainebula 2025-07-13 00:47:57 +08:00
  • 918b31635a disable warning info: train_group_size is None hanhainebula 2025-07-13 00:42:30 +08:00
  • a702343812 Merge pull request #1491 from hanhainebula/master Jianlyu Chen 2025-07-12 17:55:53 +08:00
  • 15876a9391 add feature: support customized train_group_size hanhainebula 2025-07-12 17:55:03 +08:00
  • 875fd4ffcb update docs ZiyiXia 2025-06-04 17:57:10 +08:00
  • 235f967a01 update tutorials ZiyiXia 2025-06-04 17:27:36 +08:00
  • 5e64baa61e Merge pull request #1466 from 545999961/master chaofan 2025-05-28 16:15:17 +08:00
  • 018b984e23 update reranker inference cfli 2025-05-28 16:14:32 +08:00
  • d04f7989ee release version 1.3.5 v1.3.5 chaofan 2025-05-28 15:12:19 +08:00
  • 8576fde79b Merge pull request #1465 from 545999961/master chaofan 2025-05-28 14:58:53 +08:00
  • bf410d51e9 update environment cfli 2025-05-28 14:55:54 +08:00
  • 97ca07325d Merge pull request #1464 from 545999961/master chaofan 2025-05-28 14:18:23 +08:00
  • b51706d63a upload coder eval script cfli 2025-05-28 14:17:19 +08:00
  • 821c387961 upload coder eval script cfli 2025-05-28 14:12:16 +08:00
  • 3332a1956e Merge pull request #1459 from 545999961/master chaofan 2025-05-22 18:07:40 +08:00
  • d412884a4e update reinforced_ir cfli 2025-05-22 18:06:43 +08:00
  • 5c11feffc1 Merge pull request #1458 from 545999961/master chaofan 2025-05-22 17:56:48 +08:00
  • 41b526441f update reinforced_ir cfli 2025-05-22 17:55:44 +08:00
  • 52bb9fddb5 Merge pull request #1457 from 545999961/master chaofan 2025-05-22 17:52:21 +08:00