katanemo

Model List | FAQ | Usage | Evaluation | Train | Contact | Citation | License For more details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - Long-Context LLM: Activation Beacon - Fine-tuning of LM : LM-Cocktail - Dense Retrieval: BGE-M3, LLM Embedder, BGE Embedding - Reranker Model: BGE Reranker - Benchmark: C-MTEB News - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model that supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical Report and Code. :fire: - 1/9/2024: Release Activation-Beacon, an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM. Technical Report :fire: - 12/24/2023: Release LLaRA, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code will be open-sourced. Please stay tuned. Technical Report :fire: - 11/23/2023: Release LM-Cocktail, a method to maintain general capabilities during fine-tuning by merging multiple language models. Technical Report :fire: - 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Technical Report - 09/15/2023: The technical report and massive training data of BGE has been released - 09/12/2023: New models: - New reranker model: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models. - update embedding model: release `bge--v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction. - 09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning. - 08/09/2023: BGE Models are integrated into Langchain, you can use it like this; C-MTEB leaderboard is available. - 08/05/2023: Release base-scale and small-scale models, best performance among the models of the same size 🤗 - 08/02/2023: Release `bge-large-`(short for BAAI General Embedding) Models, rank 1st on MTEB and C-MTEB benchmark! :tada: :tada: - 08/01/2023: We release the Chinese Massive Text Embedding Benchmark (C-MTEB), consisting of 31 test dataset. | Model | Language | | Description | query instruction for retrieval [1] | |:-------------------------------|:--------:| :--------:| :--------:|:--------:| | BAAI/bge-m3 | Multilingual | Inference Fine-tune | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | | | BAAI/llm-embedder | English | Inference Fine-tune | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See README | | BAAI/bge-reranker-large | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | | | BAAI/bge-reranker-base | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | | | BAAI/bge-large-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-base-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-small-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-large-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | BAAI/bge-base-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | BAAI/bge-small-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` | | BAAI/bge-large-en | English | Inference Fine-tune | :trophy: rank 1st in MTEB leaderboard | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-base-en | English | Inference Fine-tune | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-small-en | English | Inference Fine-tune |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` | | BAAI/bge-large-zh | Chinese | Inference Fine-tune | :trophy: rank 1st in C-MTEB benchmark | `为这个句子生成表示以用于检索相关文章：` | | BAAI/bge-base-zh | Chinese | Inference Fine-tune | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：` | | BAAI/bge-small-zh | Chinese | Inference Fine-tune | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：` | [1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, no instruction needs to be added to passages. [2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models. For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results. All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI. If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models . Following this example to prepare data and fine-tune your model. Some suggestions: - Mine hard negatives following this example, which can improve the retrieval performance. - If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity. - If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker. 2. The similarity score between two dissimilar sentences is higher than 0.5 Suggest to use bge v1.5, which alleviates the issue of the similarity distribution. Since we finetune the models by contrastive learning with a temperature of 0.01, the similarity distribution of the current BGE model is about in the interval \[0.6, 1\]. So a similarity score greater than 0.5 does not indicate that the two sentences are similar. For downstream tasks, such as passage retrieval or semantic similarity, what matters is the relative order of the scores, not the absolute value. If you need to filter similar sentences based on a similarity threshold, please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9). For the `bge--v1.5`, we improve its retrieval ability when not using instruction. No instruction only has a slight degradation in retrieval performance compared with using instruction. So you can generate embedding without instruction in all cases for convenience. For a retrieval task that uses short queries to find long related documents, it is recommended to add instructions for these short queries. The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task. In all cases, the documents/passages do not need to add the instruction. Here are some examples for using `bge` models with FlagEmbedding, Sentence-Transformers, Langchain, or Huggingface Transformers. If it doesn't work for you, you can see FlagEmbedding for more methods to install FlagEmbedding. For the value of the argument `queryinstructionforretrieval`, see Model List. By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDAVISIBLEDEVICES"]` to select specific GPUs. You also can set `os.environ["CUDAVISIBLEDEVICES"]=""` to make all GPUs unavailable. You can also use the `bge` models with sentence-transformers: For s2p(short query to long passage) retrieval task, each short query should start with an instruction (instructions see Model List). But the instruction is not needed for passages. With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding. Its also possible to deploy the onnx files with the infinityemb pip package. Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range. Get relevance scores (higher scores indicate more relevance): `baai-general-embedding` models achieve state-of-the-art performance on both MTEB and C-MTEB leaderboard! For more details and evaluation tools see our scripts. | Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) | |:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | BAAI/bge-large-en-v1.5 | 1024 | 512 | 64.23 | 54.29 | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 | | BAAI/bge-base-en-v1.5 | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 | | BAAI/bge-small-en-v1.5 | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 | | bge-large-en | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 | | bge-base-en | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 | | gte-large | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 | | gte-base | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 | | e5-large-v2 | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 | | bge-small-en | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 | | instructor-xl | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 | | e5-base-v2 | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 | | gte-small | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 | | text-embedding-ada-002 | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 | | e5-small-v2 | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 | | sentence-t5-xxl | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 | | all-mpnet-base-v2 | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 | | sgpt-bloom-7b1-msmarco | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 | - C-MTEB: We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks. Please refer to CMTEB for a detailed introduction. | Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | BAAI/bge-large-zh-v1.5 | 1024 | 64.53 | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 | | BAAI/bge-base-zh-v1.5 | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 | | BAAI/bge-small-zh-v1.5 | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 | | BAAI/bge-large-zh | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 | | bge-large-zh-noinstruct | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 | | BAAI/bge-base-zh | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 | | multilingual-e5-large | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 | | BAAI/bge-small-zh | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 | | m3e-base | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 | | m3e-large | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 | | multilingual-e5-base | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 | | multilingual-e5-small | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 | | text-embedding-ada-002(OpenAI) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 | | luotuo | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 | | text2vec-base | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 | | text2vec-large | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 | | Model | T2Reranking | T2RerankingZh2En\ | T2RerankingEn2Zh\ | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg | |:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 | | multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 | | multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 | | multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 | | m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 | | m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 | | bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 | | bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 | | BAAI/bge-reranker-base | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 | | BAAI/bge-reranker-large | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 | \ : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks We pre-train the models using retromae and train them on large-scale pairs data using contrastive learning. You can fine-tune the embedding model on your data following our examples. We also provide a pre-train example. Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned. More training details for bge see baaigeneralembedding. Cross-encoder will perform full-attention over the input pair, which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model. Therefore, it can be used to re-rank the top-k documents returned by embedding model. We train the cross-encoder on a multilingual pair data, The data format is the same as embedding model, so you can fine-tune it easily following our example. More details please refer to ./FlagEmbedding/reranker/README.md Contact If you have any question or suggestion related to this project, feel free to open an issue or pull request. You also can email Shitao Xiao([email protected]) and Zheng Liu([email protected]). If you find this repository useful, please consider giving a star :star: and citation License FlagEmbedding is licensed under the MIT License. The released models can be used for commercial purposes free of charge.

Overview With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique to opera...

Overview The Katanemo Arch-Function collection of large language models (LLMs) is a collection state-of-the-art (SOTA) LLMs specifically designed for function calling tasks. The models are designed to understand complex function signatures, identify required parameters, and produce accurate function call outputs based on natural language prompts. Achieving performance on par with GPT-4, these models set a new benchmark in the domain of function-oriented tasks, making them suitable for scenarios where automated API interaction and function execution is crucial. In summary, the Katanemo Arch-Function collection demonstrates: - State-of-the-art performance in function calling - Accurate parameter identification and suggestion, even in ambiguous or incomplete inputs - High generalization across multiple function calling use cases, from API interactions to automated backend tasks. - Optimized low-latency, high-throughput performance, making it suitable for real-time, production environments. Arch-Function is the core LLM used in then open source Arch project. An AI-native proxy server for AI that offers unified access and intelligent routing to LLMs. Single Function Calling Call only one function per user query Parallel Function Calling Call the same function multiple times but with different set of parameter values Multiple Function Calling Call different functions per user query Parallel & Multiple Perform both parallel and multiple function calling Training Details Katanemo Arch-Function collection is built on top of the Qwen 2.5. A blog with technical details leading to our models will be published soon. Performance Benchmarks We evaluate Katanemo Arch-Function series on the Berkeley Function-Calling Leaderboard (BFCL). We compare with commonly-used models and the results (as of Oct 21st, 2024) are shwon below. For each model family, we select the one with the highest rank. Rank Model Overall Single Turn Multi Turn Hallucination Non-live (AST) Non-live (Exec) Live (AST) Overall Relevance Irrelevance 1 GPT-4o-2024-08-06 (FC) 62.19% 85.90% 85.64% 75.43% 25.00% 63.41% 82.93% Arch-Function-7B 59.62% 86.83% 88.07% 71.57% 21.00% 95.12% 73.63% 6 o1-preview-2024-09-12 (Prompt) 59.27% 86.42% 88.88% 73.08% 17.62% 73.17% 74.60% 9 Gemini-1.5-Flash-002 (Prompt) 57.92% 86.58% 89.48% 76.28% 9.88% 85.37% 78.54% Arch-Function-3B 57.69% 85.19% 86.18% 71.21% 17.50% 90.24% 72.88% 12 Claude-3.5-Sonnet-20240620 (FC) 57.42% 70.04% 66.27% 74.68% 28.38% 68.29% 74.58% 13 mistral-large-2407 (FC) 56.80% 86.62% 84.57% 68.37% 20.62% 75.61% 49.44% Arch-Function-1.5B 56.20% 84.40% 83.96% 69.36% 15.88% 87.80% 74.39% 21 Llama-3.1-70B-Instruct (Prompt) 53.67% 88.90% 89.34% 61.13% 12.38% 92.68% 58.38% 22 Gemma-2-27b-it (Prompt) 53.66% 88.52% 87.89% 69.48% 4.12% 87.8% 68.76% Requirements The code of Arch-Function-3B has been in the Hugging Face `transformers` library and we advise you to install latest version: How to use We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the function-calling mode of ChatGPT. Then you should be able to see the following output string in JSON format: ` Multi Turn Example Upon getting results from functions, you can add it to the `messages` list as a `user` message and pass it to the model to get responses for users. Then you should be able to see the following output: License Katanemo Arch-Function collection is distributed under the Katanemo license.