Skip to content

Commit bb93567

Browse files
hanhainebulahanhainebula
committed
update README for new models
1 parent a740003 commit bb93567

2 files changed

Lines changed: 4 additions & 3 deletions

File tree

‎README.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -162,6 +162,7 @@ Refer to our [report: c-pack](https://arxiv.org/pdf/2309.07597.pdf) and [code](h
162162
| Model | Language | | Description | query instruction for retrieval |
163163
|:--------------------------------------------------------------------------|:--------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|
164164
| [BAAI/bge-en-icl](https://huggingface.co/BAAI/bge-en-icl) | English | | A LLM-based embedding model with in-context learning capabilities, which can fully leverage the model's potential based on a few shot examples | Provide instructions and few-shot examples freely based on the given task. |
165+
| [BAAI/bge-multilingual-gemma2](https://huggingface.co/BAAI/bge-multilingual-gemma2) | Multilingual | - | A LLM-based multilingual embedding model, trained on a diverse range of languages and tasks. | Provide instructions based on the given task. |
165166
| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3#usage) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3) | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | |
166167
| [LM-Cocktail](https://huggingface.co/Shitao) | English | | fine-tuned models (Llama and BGE) which can be used to reproduce the results of LM-Cocktail | |
167168
| [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) |

‎README_zh.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -36,10 +36,10 @@ FlagEmbedding专注于检索增强llm领域，目前包括以下项目:
3636
- **Benchmark**: [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB), [AIR-Bench](https://github.com/AIR-Bench/AIR-Bench), [MLVU](https://github.com/JUNJIE99/MLVU)
3737

3838
## 更新
39-
- 7/26/2024：发布[bge-en-icl](https://huggingface.co/BAAI/bge-en-icl)。这是一个结合了上下文学习能力的文本检索模型，通过提供与任务相关的查询-回答示例，可以编码语义更丰富的查询，进一步增强嵌入的语义表征能力。:fire:
40-
- 7/26/2024: 发布[bge-multilingual-gemma2](https://huggingface.co/BAAI/bge-multilingual-gemma2)。这是一个基于gemma-2-9b的多语言文本向量模型，同时支持多种语言和多样的下游任务，在多语言检索数据集 MIRACL, MTEB-fr, MTEB-pl 上取得了迄今最好的实验结果。:fire:
39+
- 7/26/2024：发布[bge-en-icl](https://huggingface.co/BAAI/bge-en-icl)。这是一个结合了上下文学习能力的文本检索模型，通过提供与任务相关的查询-回答示例，可以编码语义更丰富的查询，进一步增强嵌入的语义表征能力。 :fire:
40+
- 7/26/2024: 发布[bge-multilingual-gemma2](https://huggingface.co/BAAI/bge-multilingual-gemma2)。这是一个基于gemma-2-9b的多语言文本向量模型，同时支持多种语言和多样的下游任务，在多语言检索数据集 MIRACL, MTEB-fr, MTEB-pl 上取得了迄今最好的实验结果。 :fire:
4141
- 7/26/2024：发布新的轻量级重排器[bge-reranker-v2.5-gemma2-lightweight](https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight)。这是一个基于gemma-2-9b的轻量级重排器，支持令牌压缩和分层轻量操作，在节省大量资源的同时，仍能确保良好的性能。:fire:
42-
- 6/7/2024: 发布首个专为长视频理解设计的全面评测基准[MLVU](https://github.com/JUNJIE99/MLVU)。MLVU拥有丰富的视频时长范围，多样化的视频来源，以及多个专为长视频理解设计的评估任务。:fire:
42+
- 6/7/2024: 发布首个专为长视频理解设计的全面评测基准[MLVU](https://github.com/JUNJIE99/MLVU)。MLVU拥有丰富的视频时长范围，多样化的视频来源，以及多个专为长视频理解设计的评估任务。 :fire:
4343
- 5/21/2024：联合 Jina AI、Zilliz、HuggingFace 等机构发布评测基准 [AIR-Bench](https://github.com/AIR-Bench/AIR-Bench)，针对检索任务和 RAG 场景设计。AIR-Bench 首次提出在检索任务中使用 LLMs 自动化生产评估数据，避免模型过拟合测试数据。AIR-Bench 不需要人工参与标注数据，因而可以更灵活覆盖更多垂直领域和不同语种。同时 AIR-Bench 会定期进行更新从而满足社区不断变化的评测需求。[Leaderboard](https://huggingface.co/spaces/AIR-Bench/leaderboard) :fire:
4444
- 4/30/2024: 发布[Llama-3-8B-Instruct-80K-QLoRA](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA), 其通过在少量合成的长文本数据上的QLoRA训练，有效地将Llama-3-8B-Instruct的上下文长度从8K扩展到80K。详见[代码](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora) :fire:
4545
- 3/18/2024: 发布新的[rerankers](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker), 拥有更好的性能同时支持多语言和长文本。 :fire:

0 commit comments

Comments
 (0)