Skip to content

Commit 23d5cbf

Browse files
545999961545999961
committed
release new model
1 parent 37c250d commit 23d5cbf

2 files changed

Lines changed: 14 additions & 0 deletions

File tree

‎README.md‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,8 @@ FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following p
3737
- **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)
3838

3939
## News
40+
- 7/26/2024: Release a new embedding model [bge-en-icl](BAAI/bge-en-icl), an embedding model that incorporates in-context learning capabilities, which, by providing task-relevant query-response examples, can encode semantically richer queries, further enhancing the semantic representation ability of the embeddings.
41+
- 7/26/2024: Release a new lightweight reranker [bge-reranker-v2.5-gemma2-lightweight](BAAI/bge-reranker-v2.5-gemma2-lightweight), a lightweight reranker based on gemma2-9B, which supports token compression and layerwise lightweight operations, can still ensure good performance while saving a significant amount of resources.
4042
- 6/7/2024: Release a new benchmark [MLVU](https://github.com/JUNJIE99/MLVU), the first comprehensive benchmark specifically designed for long video understanding. MLVU features an extensive range of video durations, a diverse collection of video sources, and a set of evaluation tasks uniquely tailored for long-form video understanding. :fire:
4143
- 5/21/2024: Release a new benchmark [AIR-Bench](https://github.com/AIR-Bench/AIR-Bench) together with Jina AI, Zilliz, HuggingFace, and other partners. AIR-Bench focuses on a fair out-of-distribution evaluation for Neural IR & RAG. It generates the synthetic data for benchmarking w.r.t. diverse domains and languages. It is dynamic and will be updated on regular basis. [Leaderboard](https://huggingface.co/spaces/AIR-Bench/leaderboard) :fire:
4244
- 4/30/2024: Release [Llama-3-8B-Instruct-80K-QLoRA](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA), extending the context length of Llama-3-8B-Instruct from 8K to 80K via QLoRA training on a few synthesized long-context data. The model achieves remarkable performance on various long-context benchmarks. [Code](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora) :fire:
@@ -158,9 +160,14 @@ Refer to our [report: c-pack](https://arxiv.org/pdf/2309.07597.pdf) and [code](h
158160

159161
| Model | Language | | Description | query instruction for retrieval |
160162
|:--------------------------------------------------------------------------|:--------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|
163+
| [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. |
161164
| [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) | |
162165
| [LM-Cocktail](https://huggingface.co/Shitao) | English | | fine-tuned models (Llama and BGE) which can be used to reproduce the results of LM-Cocktail | |
163166
| [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) |
167+
| [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | Multilingual | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a lightweight cross-encoder model, possesses strong multilingual capabilities, easy to deploy, with fast inference. | |
168+
| [BAAI/bge-reranker-v2-gemma](https://huggingface.co/BAAI/bge-reranker-v2-gemma) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) | a cross-encoder model which is suitable for multilingual contexts, performs well in both English proficiency and multilingual capabilities. | |
169+
| [BAAI/bge-reranker-v2-minicpm-layerwise](https://huggingface.co/BAAI/bge-reranker-v2-minicpm-layerwise) | Multilingual | [Inference](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) | a cross-encoder model which is suitable for multilingual contexts, performs well in both English and Chinese proficiency, allows freedom to select layers for output, facilitating accelerated inference. | |
170+
| [BAAI/bge-reranker-v2.5-gemma2-lightweight](https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight) | Multilingual | [Inference](BAAI/bge-reranker-v2.5-gemma2-lightweight) | a cross-encoder model which is suitable for multilingual contexts, performs well in both English and Chinese proficiency, allows freedom to select layers, compress ratio and compress layers for output, facilitating accelerated inference. | |
164171
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient | |
165172
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient | |
166173
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |

‎README_zh.md‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -36,6 +36,8 @@ 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://chat.xiaoai.plus/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。🔥
40+
- 7/26/2024：发布新的轻量级重排器[bge-reranker-v2.5-gemma2-lightweight](https://chat.xiaoai.plus/BAAI/bge-reranker-v2.5-gemma2-lightweight)。这是一个基于gemma2-9B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。🔥
3941
- 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。🔥
4042
- 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:
4143
- 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:
@@ -140,9 +142,14 @@ BGE Embedding是一个通用向量模型。 我们使用[retromae](https://githu
140142
## 模型列表
141143
| Model | Language | | Description | query instruction for retrieval [1] |
142144
|:--------------------------------------------------------------------------|:-------------------:| :--------:|:--------------------------------------:|:--------:|
145+
| [BAAI/bge-en-icl](https://huggingface.co/BAAI/bge-en-icl) | English | | 基于大型语言模型的向量模型，具有上下文学习能力，能够基于少量示例充分发挥模型的潜力。 | 根据给定的任务自由提供指示和少数示例。 |
143146
| [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | Multilingual | [推理](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3#usage) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/BGE_M3) | 多功能（向量检索，稀疏检索，多表征检索）、多语言、多粒度（最大长度8192） | |
144147
| [LM-Cocktail](https://huggingface.co/Shitao) | English | | 微调的Llama和BGE模型，可以用来复现LM-Cocktail论文的结果 | |
145148
| [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [推理](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) | 专为大语言模型各种检索增强任务设计的向量模型 | 详见 [README](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_embedder) |
149+
| [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | Multilingual | [推理](#usage-for-reranker) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | 一个轻量级的交叉编码器模型，具有强大的多语言能力，易于部署，具有快速的推理能力。 | |
150+
| [BAAI/bge-reranker-v2-gemma](https://huggingface.co/BAAI/bge-reranker-v2-gemma) | Multilingual | [推理](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) | 一个支持多语言的交叉编码器模型，在英文和多语言能力方面均表现出色。 | |
151+
| [BAAI/bge-reranker-v2-minicpm-layerwise](https://huggingface.co/BAAI/bge-reranker-v2-minicpm-layerwise) | Multilingual | [推理](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker) | 一个支持多语言的交叉编码器模型，在英文和中文方面均表现良好，允许自由选择输出层，以便加速推理。 | |
152+
| [BAAI/bge-reranker-v2.5-gemma2-lightweight](https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight) | Multilingual | [推理](BAAI/bge-reranker-v2.5-gemma2-lightweight) | 一个支持多语言的跨编码器模型，不仅在英文和中文上表现良好，还允许自由选择输出层、压缩比例和压缩层，从而便于加速推理。 | |
146153
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [推理](#usage-for-reranker) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | 交叉编码器模型，精度比向量模型更高但推理效率较低 [2] | |
147154
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [推理](#usage-for-reranker) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | 交叉编码器模型，精度比向量模型更高但推理效率较低 [2] | |
148155
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [推理](#usage-for-embedding-model) [微调](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | 1.5版本，相似度分布更加合理 | `Represent this sentence for searching relevant passages: ` |

0 commit comments

Comments
 (0)