https://huggingface.co/blog/alvarobartt/replacing-judges-with-juries-distilabel","text":"Dataset generated for the post at https://huggingface.co/blog/alvarobartt/replacing-judges-with-juries-distilabel"},"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/replacing-judges-with-juries-distilabel","lastModified":"2024-05-08T16:31:45.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false}],"position":2,"theme":"green","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/aif-datasets-with-distilabel-6565da7040440ddcc06101bd","upvotes":1,"isUpvotedByUser":false},{"slug":"alvarobartt/apple-mlx-compatible-7b-llms-on-the-hub-658319f3d7327de57a9d2ee6","title":"Apple MLX-compatible 7B LLMs on the 🤗 Hub","description":"This collection contains the model weights for 7B LLMs for Apple's MLX framework. Find more information at https://github.com/ml-explore/mlx","lastUpdated":"2024-05-07T07:40:29.110Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"items":[{"_id":"658c2f5be15da20cd88d7e50","position":0,"type":"model","author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/notus-7b-v1-mlx","lastModified":"2023-12-27T18:31:15.000Z","likes":1,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"_id":"6583f0d640e42901d6583d00","position":1,"type":"model","author":"mlx-community","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/623c830997ddced06d78699b/3qTjC7d3YFCJTwpxd2noq.png","fullname":"MLX Community","name":"mlx-community","type":"org","isHf":false,"isEnterprise":false},"downloads":3,"gated":false,"id":"mlx-community/zephyr-7b-beta","lastModified":"2023-12-27T18:31:00.000Z","likes":12,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"_id":"65831a54072be4f21ce4e14a","position":2,"type":"model","author":"mlx-community","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/623c830997ddced06d78699b/3qTjC7d3YFCJTwpxd2noq.png","fullname":"MLX Community","name":"mlx-community","type":"org","isHf":false,"isEnterprise":false},"downloads":138,"gated":false,"id":"mlx-community/Mistral-7B-Instruct-v0.2","lastModified":"2023-12-23T19:04:06.000Z","likes":19,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"_id":"65831a96b02f38ef34622e6d","position":3,"type":"model","author":"mlx-community","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/623c830997ddced06d78699b/3qTjC7d3YFCJTwpxd2noq.png","fullname":"MLX Community","name":"mlx-community","type":"org","isHf":false,"isEnterprise":false},"downloads":33,"gated":false,"id":"mlx-community/mistral-7B-v0.1","lastModified":"2023-12-20T19:13:19.000Z","likes":11,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false}],"position":3,"theme":"purple","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/apple-mlx-compatible-7b-llms-on-the-hub-658319f3d7327de57a9d2ee6","upvotes":9,"isUpvotedByUser":false},{"slug":"alvarobartt/ner-in-spanish-650eb2fec305ec67e6066f92","title":"NER in Spanish","description":"Fine-tuned models to perform NER in Spanish using the framework SpanMarker and different encoders and datasets","lastUpdated":"2024-05-07T07:40:29.121Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"items":[{"_id":"65155499cd5e6f5c227dcca8","position":0,"type":"model","author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":82,"gated":false,"id":"alvarobartt/bert-base-multilingual-cased-ner-spanish","lastModified":"2023-10-17T10:47:53.000Z","likes":2,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"_id":"650eb329dba31194cb37dbe3","position":1,"type":"model","author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":1,"gated":false,"id":"alvarobartt/span-marker-xlm-roberta-large-conll-2002-es","lastModified":"2023-09-23T09:41:31.000Z","likes":1,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"_id":"6512e04742a541c175211403","position":2,"type":"model","author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/span-marker-roberta-base-bne-conll-2002-es","lastModified":"2023-09-26T13:39:01.000Z","likes":1,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false}],"position":4,"theme":"indigo","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/ner-in-spanish-650eb2fec305ec67e6066f92","upvotes":4,"isUpvotedByUser":false},{"slug":"alvarobartt/datasets-in-spanish-for-llm-evaluation-65df420be6754afd1b5b8831","title":"🇪🇸 Datasets in Spanish for LLM Evaluation ","description":"This collection contains some datasets for LLM evaluation in Spanish, from nlp.uoregon.edu, translated using ChatGPT (including English counterparts)","lastUpdated":"2024-05-07T07:40:29.308Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"items":[{"_id":"65df42584d436404cdd3b8cd","position":0,"type":"dataset","note":{"html":"ARC-Challenge translated version using ChatGPT","text":"ARC-Challenge translated version using ChatGPT"},"author":"alvarobartt","downloads":21,"gated":false,"id":"alvarobartt/arc-c-okapi-eval-es","lastModified":"2024-02-28T13:46:26.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2585,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"_id":"65e07ee849e15a5bc6526d5e","position":1,"type":"dataset","note":{"html":"MMLU translated version of all the subsets and splits (besides the `auxiliary_train` one) using ChatGPT","text":"MMLU translated version of all the subsets and splits (besides the `auxiliary_train` one) using ChatGPT"},"author":"alvarobartt","downloads":260,"gated":false,"id":"alvarobartt/mmlu-okapi-eval-es","lastModified":"2024-02-29T17:57:41.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":15071,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"_id":"65e071c191899c8d70ff4f98","position":2,"type":"dataset","note":{"html":"HellaSwag translated version of the `validation` split using ChatGPT","text":"HellaSwag translated version of the `validation` split using ChatGPT"},"author":"alvarobartt","downloads":1,"gated":false,"id":"alvarobartt/hellaswag-okapi-eval-es","lastModified":"2024-02-29T12:32:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":9374,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false},{"_id":"65df424438cddb13aaba7786","position":3,"type":"dataset","note":{"html":"TruthfulQA translated version of the `multiple_choice` subset using ChatGPT (doesn't contain English counterpart)","text":"TruthfulQA translated version of the `multiple_choice` subset using ChatGPT (doesn't contain English counterpart)"},"author":"alvarobartt","downloads":1,"gated":false,"id":"alvarobartt/truthfulqa-okapi-eval-es","lastModified":"2024-02-28T12:14:53.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":789,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false}],"position":5,"theme":"pink","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/datasets-in-spanish-for-llm-evaluation-65df420be6754afd1b5b8831","upvotes":0,"isUpvotedByUser":false},{"slug":"alvarobartt/from-zero-to-gpt-hero-650b112cee5dfd0c2a5e0ecb","title":"From zero to GPT-hero","description":"Reading list to fully understand GPT (and GPT-2) and to be able to implement those from scratch","lastUpdated":"2024-05-07T07:40:29.113Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"items":[{"_id":"650b11fd15283a72dfd69320","position":0,"type":"paper","note":{"html":"Useful to have more insights about the tokenizer trained and used for GPT-2, which is a modified BPE as defined in this paper. Additionally, it's implemented in `tiktoken` at https://github.com/openai/tiktoken","text":"Useful to have more insights about the tokenizer trained and used for GPT-2, which is a modified BPE as defined in this paper. Additionally, it's implemented in `tiktoken` at https://github.com/openai/tiktoken"},"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/1508.07909.png","upvotes":4,"publishedAt":"2015-08-31T16:37:31.000Z","isUpvotedByUser":false},{"_id":"650b112cee5dfd0c2a5e0ecc","position":1,"type":"paper","note":{"html":"Attention is explained after being introduced at https://arxiv.org/abs/1409.0473, this paper proposed an Encoder-Decoder architecture, the Transformer. The whole architecture is interesting, but we'll transition into Decoder-only architectures for GPT.","text":"Attention is explained after being introduced at https://arxiv.org/abs/1409.0473, this paper proposed an Encoder-Decoder architecture, the Transformer. The whole architecture is interesting, but we'll transition into Decoder-only architectures for GPT."},"id":"1706.03762","title":"Attention Is All You Need","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/1706.03762.png","upvotes":34,"publishedAt":"2017-06-12T17:57:34.000Z","isUpvotedByUser":false},{"_id":"650b1250b2a2e14eaefee98f","position":2,"type":"paper","note":{"html":"Is interesting even though not comparable to GPT-2, as it's build using the encoder blocks and it's not auto-regressive in nature, but adds context on both sides of a word to achieve better results. But nice to read before GPT-2 to understand the differences and why it's been a relevant architecture.","text":"Is interesting even though not comparable to GPT-2, as it's build using the encoder blocks and it's not auto-regressive in nature, but adds context on both sides of a word to achieve better results. But nice to read before GPT-2 to understand the differences and why it's been a relevant architecture."},"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language\n Understanding","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/1810.04805.png","upvotes":11,"publishedAt":"2018-10-11T00:50:01.000Z","isUpvotedByUser":false},{"_id":"650b1307fac8d3e64a9a2317","position":3,"type":"paper","note":{"html":"Introduces the concept of Decoder-only architectures, which is later on adopted by GPT.","text":"Introduces the concept of Decoder-only architectures, which is later on adopted by GPT."},"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/1801.10198.png","upvotes":3,"publishedAt":"2018-01-30T20:07:01.000Z","isUpvotedByUser":false}],"position":7,"theme":"green","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/from-zero-to-gpt-hero-650b112cee5dfd0c2a5e0ecb","upvotes":0,"isUpvotedByUser":false},{"slug":"alvarobartt/papers-i-have-will-read-in-2024-6596d718185db9437098d429","title":"Papers I have / will read in 2024","description":"This collection contains all the papers (on ArXiv) that either I've read or I will read in 2024, including a short summary / conclusion","lastUpdated":"2024-05-07T07:40:34.477Z","owner":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"items":[{"_id":"6596d77702a265cc8009871b","position":0,"type":"paper","note":{"html":"Got to generate this after reading it for the first time https://hf.co/datasets/alvarobartt/improving-text-embeddings-with-llms , but still missing too many pieces to put together a `distilabel` pipeline to easily generate the whole dataset (still closed sourced, unreleased)","text":"Got to generate this after reading it for the first time https://hf.co/datasets/alvarobartt/improving-text-embeddings-with-llms , but still missing too many pieces to put together a `distilabel` pipeline to easily generate the whole dataset (still closed sourced, unreleased)"},"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2401.00368.png","upvotes":72,"publishedAt":"2023-12-31T02:13:18.000Z","isUpvotedByUser":false},{"_id":"6623c6aa82e322b92de7acd6","position":1,"type":"paper","id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2404.10719.png","upvotes":3,"publishedAt":"2024-04-16T16:51:53.000Z","isUpvotedByUser":false},{"_id":"6623c6b111772517e5865feb","position":2,"type":"paper","id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited\n Context Length","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2404.08801.png","upvotes":61,"publishedAt":"2024-04-12T20:28:14.000Z","isUpvotedByUser":false},{"_id":"6623c6bb2e1aa351ad96f773","position":3,"type":"paper","id":"2404.08634","title":"Pre-training Small Base LMs with Fewer Tokens","thumbnailUrl":"https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2404.08634.png","upvotes":32,"publishedAt":"2024-04-12T17:53:34.000Z","isUpvotedByUser":false}],"position":9,"theme":"purple","private":false,"shareUrl":"https://huggingface.co/collections/alvarobartt/papers-i-have-will-read-in-2024-6596d718185db9437098d429","upvotes":0,"isUpvotedByUser":false}],"datasets":[{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/Capybara-Preferences-Tiny","lastModified":"2024-05-14T17:25:20.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/example-distilabel","lastModified":"2024-05-10T08:54:53.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/replacing-judges-with-juries-distilabel","lastModified":"2024-05-08T16:31:45.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-eval-distilabel-default","lastModified":"2024-05-07T07:27:13.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-eval-distilabel-ratings","lastModified":"2024-05-07T07:22:07.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-eval-distilabel-generation","lastModified":"2024-05-07T07:21:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-eval-distilabel-index","lastModified":"2024-05-07T07:20:31.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-eval-distilabel","lastModified":"2024-05-07T07:19:32.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/prometheus-abs-eval-distilabel","lastModified":"2024-05-06T09:45:25.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/harry-potter-genstruct","lastModified":"2024-05-02T13:01:31.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/mini-capybara-100","lastModified":"2024-04-03T17:07:27.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/airoboros2.2-pref-10k","lastModified":"2024-03-28T08:43:01.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10000,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":117,"gated":false,"id":"alvarobartt/dpo-mix-7k-simplified","lastModified":"2024-03-26T08:23:36.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":7500,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":11,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-mini","lastModified":"2024-03-22T12:24:26.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/self-alignment-with-instruction-backtranslation","lastModified":"2024-03-20T12:30:03.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":327,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/instruction-dataset-notus-7b-v1-inference-endpoints","lastModified":"2024-03-20T08:51:34.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":327,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/evol-instruct-logging","lastModified":"2024-03-19T12:05:23.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/evol-instruct-sample","lastModified":"2024-03-12T13:09:59.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":14,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/evol-instruct","lastModified":"2024-03-11T18:34:00.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/evol-instruct-test","lastModified":"2024-03-11T10:45:56.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":30,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/distilabel-test","lastModified":"2024-03-08T08:37:14.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/logging","lastModified":"2024-03-05T12:36:53.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":8,"gated":false,"id":"alvarobartt/instruction-dataset-mistral-7b-instruct-v0.2","lastModified":"2024-03-01T13:22:57.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":327,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":260,"gated":false,"id":"alvarobartt/mmlu-okapi-eval-es","lastModified":"2024-02-29T17:57:41.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":15071,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":1,"gated":false,"id":"alvarobartt/hellaswag-okapi-eval-es","lastModified":"2024-02-29T12:32:35.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":9374,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/openhermes-preferences-coding","lastModified":"2024-02-29T09:15:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":5460,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":1,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/openhermes-preferences-metamath","lastModified":"2024-02-29T09:14:42.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":56444,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false},{"author":"alvarobartt","downloads":21,"gated":false,"id":"alvarobartt/arc-c-okapi-eval-es","lastModified":"2024-02-28T13:46:26.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2585,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":1,"gated":false,"id":"alvarobartt/truthfulqa-okapi-eval-es","lastModified":"2024-02-28T12:14:53.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":789,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/distilabel","lastModified":"2024-02-27T12:34:12.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/instruction-dataset","lastModified":"2024-02-26T12:30:08.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/test","lastModified":"2024-02-23T09:37:14.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":4,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/Capybara_openai","lastModified":"2024-02-06T14:02:06.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":16006,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/orca_dpo_pairs_openai","lastModified":"2024-02-06T10:01:14.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":12859,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/HelpSteer-AIF-raw","lastModified":"2024-02-06T07:33:28.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1000,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/HelpSteer-AIF","lastModified":"2024-02-06T07:32:41.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":1000,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":5,"isLikedByUser":false},{"author":"alvarobartt","downloads":1,"gated":false,"id":"alvarobartt/improving-text-embeddings-with-llms","lastModified":"2024-02-02T15:34:51.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":200,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":4,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/evol-instruct-from-ultrafeedback","lastModified":"2024-01-05T18:17:37.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10000,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-multi-binarized-quality-preferences-cleaned","lastModified":"2023-12-20T10:14:40.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":154663,"tags":["croissant"],"libraries":["datasets","dask","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/gists","lastModified":"2023-12-16T17:53:15.000Z","private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/Anthropic_HH_Golden_Formatted","lastModified":"2023-12-14T10:01:59.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":44849,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":2,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/Anthropic_HH_Golden_Extended","lastModified":"2023-12-14T10:01:29.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":89698,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-binarized-preferences-clean","lastModified":"2023-12-05T08:43:28.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":63136,"tags":["croissant"],"libraries":["datasets","dask","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/zephyr-7b-beta-judgelm-new-test","lastModified":"2023-11-17T14:13:43.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/zephyr-7b-beta-judgelm-new-small","lastModified":"2023-11-14T09:40:38.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":19,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/stack-exchange-paired-mini","lastModified":"2023-11-10T09:54:18.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/zephyr-7b-beta-judgelm","lastModified":"2023-11-09T16:23:44.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-enable-checkpoint-100","lastModified":"2023-11-09T10:06:20.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/social-reasoning-rlhf-ULTRAFEEDBACK-honesty","lastModified":"2023-11-07T12:46:07.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":100,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/judgelm-instruction-dataset-mini","lastModified":"2023-11-03T11:48:42.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-instruction-dataset-mini","lastModified":"2023-11-03T11:30:49.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":6,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false},{"author":"alvarobartt","downloads":0,"gated":false,"id":"alvarobartt/ultrafeedback-instruction-dataset","lastModified":"2023-10-31T14:51:34.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":50,"tags":["croissant"],"libraries":["datasets","pandas","mlcroissant"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false}],"hasMoreActivities":false,"models":[{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":995,"gated":false,"id":"alvarobartt/mistral-7b-orpo-capybara-reproduction","lastModified":"2024-03-28T15:41:51.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":984,"gated":false,"id":"alvarobartt/mistral-7b-orpo-airoboros-pref-10k","lastModified":"2024-03-28T12:45:40.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":992,"gated":false,"id":"alvarobartt/mistral-7b-orpo-alignment-handbook","lastModified":"2024-03-27T13:42:29.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":3,"gated":false,"id":"alvarobartt/mistral-orpo-mix-b0.05-l1024-pl512-lr5e-7-cosine","lastModified":"2024-03-26T09:46:26.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":6,"gated":false,"id":"alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt","lastModified":"2024-03-26T09:40:59.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":9,"gated":false,"id":"alvarobartt/mistral-orpo-mix","lastModified":"2024-03-24T15:11:33.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":1008,"gated":false,"id":"alvarobartt/Mistral-7B-v0.1-ORPO","lastModified":"2024-03-23T10:22:44.000Z","likes":15,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":1,"gated":false,"id":"alvarobartt/Mistral-7B-v0.1-ORPO-PEFT","lastModified":"2024-03-23T09:30:53.000Z","likes":1,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/zephyr-gemma-dpo-no-gen-prompt","lastModified":"2024-03-12T11:50:32.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":3,"gated":false,"id":"alvarobartt/zephyr-gemma-dpo","lastModified":"2024-03-12T10:18:06.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/notus-7b-v1-mlx","lastModified":"2023-12-27T18:31:15.000Z","likes":1,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/notus-7b-v1-mlx-4bit","lastModified":"2023-12-27T18:30:25.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":162,"gated":false,"id":"alvarobartt/UltraCM-13B-GGUF","lastModified":"2023-12-14T11:45:16.000Z","likes":4,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":103,"gated":false,"id":"alvarobartt/lince-zero-7b-GGUF","lastModified":"2023-11-01T20:39:19.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":82,"gated":false,"id":"alvarobartt/bert-base-multilingual-cased-ner-spanish","lastModified":"2023-10-17T10:47:53.000Z","likes":2,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":1,"gated":false,"id":"alvarobartt/distilbert-base-cased-ner","lastModified":"2023-10-05T12:21:26.000Z","likes":0,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":2,"gated":false,"id":"alvarobartt/span-marker-roberta-base-bne-conll-2002-es","lastModified":"2023-09-26T13:39:01.000Z","likes":1,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":1,"gated":false,"id":"alvarobartt/span-marker-xlm-roberta-large-conll-2002-es","lastModified":"2023-09-23T09:41:31.000Z","likes":1,"pipeline_tag":"token-classification","private":false,"repoType":"model","isLikedByUser":false},{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"downloads":0,"gated":false,"id":"alvarobartt/bert_tiny_en_uncased-finetuned-sst-2-english","lastModified":"2023-05-15T14:01:00.000Z","likes":0,"pipeline_tag":"text-classification","private":false,"repoType":"model","isLikedByUser":false}],"numberLikes":243,"papers":[],"posts":[{"slug":"898938685374933","content":[{"type":"text","value":"🔥 Prometheus 2 was recently released by Kaist AI as an alternative and closely mirroring both human and GPT-4 evaluation, and surpassing the former Prometheus!","raw":"🔥 Prometheus 2 was recently released by Kaist AI as an alternative and closely mirroring both human and GPT-4 evaluation, and surpassing the former Prometheus!"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"resource","resource":{"type":"model","id":"prometheus-eval/prometheus-7b-v2.0"},"url":"https://huggingface.co/prometheus-eval/prometheus-7b-v2.0","raw":"https://huggingface.co/prometheus-eval/prometheus-7b-v2.0"},{"type":"new_line","raw":"\n"},{"type":"resource","resource":{"type":"model","id":"prometheus-eval/prometheus-8x7b-v2.0"},"url":"https://huggingface.co/prometheus-eval/prometheus-8x7b-v2.0","raw":"https://huggingface.co/prometheus-eval/prometheus-8x7b-v2.0"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"🌬️Fine-tuned on top of ","raw":"🌬️Fine-tuned on top of "},{"type":"resource","resource":{"type":"model","id":"mistralai/Mistral-7B-Instruct-v0.2"},"url":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2","raw":"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2"},{"type":"text","value":" and ","raw":" and "},{"type":"resource","resource":{"type":"model","id":"mistralai/Mixtral-8x7B-Instruct-v0.1"},"url":"https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1","raw":"https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1"},{"type":"new_line","raw":"\n"},{"type":"text","value":"🗂️The datasets used for fine-tuning have been publicly released i.e. ","raw":"🗂️The datasets used for fine-tuning have been publicly released i.e. "},{"type":"resource","resource":{"type":"dataset","id":"prometheus-eval/Feedback-Collection"},"url":"https://huggingface.co/datasets/prometheus-eval/Feedback-Collection","raw":"https://huggingface.co/datasets/prometheus-eval/Feedback-Collection"},{"type":"text","value":" and ","raw":" and "},{"type":"resource","resource":{"type":"dataset","id":"prometheus-eval/Preference-Collection"},"url":"https://huggingface.co/datasets/prometheus-eval/Preference-Collection","raw":"https://huggingface.co/datasets/prometheus-eval/Preference-Collection"},{"type":"new_line","raw":"\n"},{"type":"text","value":"🤝🏻Unified LM evaluator for absolute (a single prompt-completion pair) and relative (two completions for a given prompt) due to model merging","raw":"🤝🏻Unified LM evaluator for absolute (a single prompt-completion pair) and relative (two completions for a given prompt) due to model merging"},{"type":"new_line","raw":"\n"},{"type":"text","value":"❌No longer needs a mandatory reference / golden answer, but can still be provided optionally","raw":"❌No longer needs a mandatory reference / golden answer, but can still be provided optionally"},{"type":"new_line","raw":"\n"},{"type":"text","value":"🔝Surpasses the former version of Prometheus, and has a high correlation with human, GPT-4, and Claude 3 Opus scores when evaluating LMs","raw":"🔝Surpasses the former version of Prometheus, and has a high correlation with human, GPT-4, and Claude 3 Opus scores when evaluating LMs"},{"type":"new_line","raw":"\n"},{"type":"text","value":"📝Apache 2.0 license","raw":"📝Apache 2.0 license"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"Long-story short, an amazing job from Kaist AI bridging the gap with LLM evaluators other than proprietary and bigger models!","raw":"Long-story short, an amazing job from Kaist AI bridging the gap with LLM evaluators other than proprietary and bigger models!"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"This week at Argilla, we decided to add a new task to use Prometheus 2 as an LLM evaluator using ","raw":"This week at Argilla, we decided to add a new task to use Prometheus 2 as an LLM evaluator using "},{"type":"inline_code","code":"distilabel","raw":"`distilabel`"},{"type":"text","value":", so we implemented ","raw":", so we implemented "},{"type":"inline_code","code":"PrometheusEval","raw":"`PrometheusEval`"},{"type":"text","value":".","raw":"."},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"😱 Using ","raw":"😱 Using "},{"type":"inline_code","code":"PrometheusEval","raw":"`PrometheusEval`"},{"type":"text","value":" running their 7B variant with vLLM in a single L40 on top of ","raw":" running their 7B variant with vLLM in a single L40 on top of "},{"type":"resource","resource":{"type":"dataset","id":"HuggingFaceH4/instruction-dataset"},"url":"https://huggingface.co/datasets/HuggingFaceH4/instruction-dataset","raw":"https://huggingface.co/datasets/HuggingFaceH4/instruction-dataset"},{"type":"text","value":", we got the 327 existing prompt-completion pairs evaluated and pushed to the Hub in less than 2 minutes!","raw":", we got the 327 existing prompt-completion pairs evaluated and pushed to the Hub in less than 2 minutes!"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"Find the generated dataset and the code at ","raw":"Find the generated dataset and the code at "},{"type":"resource","resource":{"type":"dataset","id":"distilabel-internal-testing/instruction-dataset-prometheus"},"url":"https://huggingface.co/datasets/distilabel-internal-testing/instruction-dataset-prometheus","raw":"https://huggingface.co/datasets/distilabel-internal-testing/instruction-dataset-prometheus"}],"rawContent":"🔥 Prometheus 2 was recently released by Kaist AI as an alternative and closely mirroring both human and GPT-4 evaluation, and surpassing the former Prometheus!\n\nhttps://huggingface.co/prometheus-eval/prometheus-7b-v2.0\nhttps://huggingface.co/prometheus-eval/prometheus-8x7b-v2.0\n\n🌬️Fine-tuned on top of https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2 and https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1\n🗂️The datasets used for fine-tuning have been publicly released i.e. https://huggingface.co/datasets/prometheus-eval/Feedback-Collection and https://huggingface.co/datasets/prometheus-eval/Preference-Collection\n🤝🏻Unified LM evaluator for absolute (a single prompt-completion pair) and relative (two completions for a given prompt) due to model merging\n❌No longer needs a mandatory reference / golden answer, but can still be provided optionally\n🔝Surpasses the former version of Prometheus, and has a high correlation with human, GPT-4, and Claude 3 Opus scores when evaluating LMs\n📝Apache 2.0 license\n\nLong-story short, an amazing job from Kaist AI bridging the gap with LLM evaluators other than proprietary and bigger models!\n\nThis week at Argilla, we decided to add a new task to use Prometheus 2 as an LLM evaluator using `distilabel`, so we implemented `PrometheusEval`.\n\n😱 Using `PrometheusEval` running their 7B variant with vLLM in a single L40 on top of https://huggingface.co/datasets/HuggingFaceH4/instruction-dataset, we got the 327 existing prompt-completion pairs evaluated and pushed to the Hub in less than 2 minutes!\n\nFind the generated dataset and the code at https://huggingface.co/datasets/distilabel-internal-testing/instruction-dataset-prometheus","author":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false,"isFollowing":false},"attachments":[],"mentions":[],"reactions":[{"reaction":"🔥","users":["matinla","lunarflu","davanstrien","andrewrreed","victor","NickyNicky","QuocKhanh","osanseviero","dhruva-sarma","shamy777"],"count":10},{"reaction":"❤️","users":["matinla","lunarflu","andrewrreed","QuocKhanh","osanseviero"],"count":5}],"publishedAt":"2024-05-08T11:04:53.000Z","updatedAt":"2024-05-08T13:41:00.840Z","commentators":[{"avatarUrl":"/avatars/5ffbcc32035ad5a5c83e45a4910c0541.svg","fullname":"matinlaghaei","name":"matinla","type":"user","isPro":false,"isHf":false,"isFollowing":false}],"url":"/posts/alvarobartt/898938685374933","totalUniqueImpressions":1684,"numComments":1},{"slug":"840376427316230","content":[{"type":"text","value":"🦫 We have just released ","raw":"🦫 We have just released "},{"type":"resource","resource":{"type":"dataset","id":"argilla/Capybara-Preferences"},"url":"https://huggingface.co/datasets/argilla/Capybara-Preferences","raw":"https://huggingface.co/datasets/argilla/Capybara-Preferences"},{"type":"text","value":" in collaboration with Kaist AI (","raw":" in collaboration with Kaist AI ("},{"type":"mention","user":"JW17","raw":"@JW17"},{"type":"text","value":", ","raw":", "},{"type":"mention","user":"nlee-208","raw":"@nlee-208"},{"type":"text","value":") and Hugging Face (","raw":") and Hugging Face ("},{"type":"mention","user":"lewtun","raw":"@lewtun"},{"type":"text","value":")","raw":")"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"A new synthetic preference dataset built using ","raw":"A new synthetic preference dataset built using "},{"type":"inline_code","code":"distilabel","raw":"`distilabel`"},{"type":"text","value":" on top of the awesome ","raw":" on top of the awesome "},{"type":"resource","resource":{"type":"dataset","id":"LDJnr/Capybara"},"url":"https://huggingface.co/datasets/LDJnr/Capybara","raw":"https://huggingface.co/datasets/LDJnr/Capybara"},{"type":"text","value":" from ","raw":" from "},{"type":"mention","user":"LDJnr","raw":"@LDJnr"},{"type":"text","value":" ","raw":" "},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"The current dataset combines the already generated alternative completions from ","raw":"The current dataset combines the already generated alternative completions from "},{"type":"resource","resource":{"type":"dataset","id":"argilla/distilabel-capybara-dpo-7k-binarized"},"url":"https://huggingface.co/datasets/argilla/distilabel-capybara-dpo-7k-binarized","raw":"https://huggingface.co/datasets/argilla/distilabel-capybara-dpo-7k-binarized"},{"type":"text","value":", while also adding the remaining ones using the same approach!","raw":", while also adding the remaining ones using the same approach!"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"Here are some key features on how we built it:","raw":"Here are some key features on how we built it:"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"- 🧹 Duplicate removal, keeping the conversation besides the last assistant response, and some slight pre-processing","raw":"- 🧹 Duplicate removal, keeping the conversation besides the last assistant response, and some slight pre-processing"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"- 🤖 Generation of alternative completions for the existing conversations (last turn only) with: ","raw":"- 🤖 Generation of alternative completions for the existing conversations (last turn only) with: "},{"type":"resource","resource":{"type":"model","id":"mlabonne/NeuralBeagle14-7B"},"url":"https://huggingface.co/mlabonne/NeuralBeagle14-7B","raw":"https://huggingface.co/mlabonne/NeuralBeagle14-7B"},{"type":"text","value":", ","raw":", "},{"type":"resource","resource":{"type":"model","id":"argilla/notus-7b-v1"},"url":"https://huggingface.co/argilla/notus-7b-v1","raw":"https://huggingface.co/argilla/notus-7b-v1"},{"type":"text","value":", and ","raw":", and "},{"type":"resource","resource":{"type":"model","id":"teknium/OpenHermes-2.5-Mistral-7B"},"url":"https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B","raw":"https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"- 👨🏻🏫 Running UltraFeedback via GPT-4 to generate the critique i.e. ratings and rationales, for the last assistant responses","raw":"- 👨🏻🏫 Running UltraFeedback via GPT-4 to generate the critique i.e. ratings and rationales, for the last assistant responses"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"- 🎉 Finally, we selected the chosen and rejected responses based on their UltraFeedback score, and applied some slight post-processing!","raw":"- 🎉 Finally, we selected the chosen and rejected responses based on their UltraFeedback score, and applied some slight post-processing!"},{"type":"new_line","raw":"\n"},{"type":"new_line","raw":"\n"},{"type":"text","value":"Sounds simple right? Start building your own synthetic datasets with ","raw":"Sounds simple right? Start building your own synthetic datasets with "},{"type":"link","href":"https://github.com/argilla-io/distilabel","raw":"https://github.com/argilla-io/distilabel"},{"type":"text","value":" already!","raw":" already!"}],"rawContent":"🦫 We have just released https://huggingface.co/datasets/argilla/Capybara-Preferences in collaboration with Kaist AI (@JW17, @nlee-208) and Hugging Face (@lewtun)\n\nA new synthetic preference dataset built using `distilabel` on top of the awesome https://huggingface.co/datasets/LDJnr/Capybara from @LDJnr \n\nThe current dataset combines the already generated alternative completions from https://huggingface.co/datasets/argilla/distilabel-capybara-dpo-7k-binarized, while also adding the remaining ones using the same approach!\n\nHere are some key features on how we built it:\n\n- 🧹 Duplicate removal, keeping the conversation besides the last assistant response, and some slight pre-processing\n\n- 🤖 Generation of alternative completions for the existing conversations (last turn only) with: https://huggingface.co/mlabonne/NeuralBeagle14-7B, https://huggingface.co/argilla/notus-7b-v1, and https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B\n\n- 👨🏻🏫 Running UltraFeedback via GPT-4 to generate the critique i.e. ratings and rationales, for the last assistant responses\n\n- 🎉 Finally, we selected the chosen and rejected responses based on their UltraFeedback score, and applied some slight post-processing!\n\nSounds simple right? Start building your own synthetic datasets with https://github.com/argilla-io/distilabel already!","author":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false,"isFollowing":false},"attachments":[],"mentions":[{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6415c043486c7c9a5d151583/fUdYFh6iVh57swCkBEy-y.jpeg","fullname":"Jiwoo Hong","name":"JW17","type":"user","isPro":false,"isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/2GjRE8z9lYNeelnBTz5ym.png","fullname":"Luigi D","name":"LDJnr","type":"user","isPro":false,"isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1594651707950-noauth.jpeg","fullname":"Lewis Tunstall","name":"lewtun","type":"user","isPro":true,"isHf":true},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6296fe6f7d586f66c3957f33/lCHe1mBVRzQ1sKsXD2OUd.jpeg","fullname":"Noah Lee","name":"nlee-208","type":"user","isPro":false,"isHf":false}],"reactions":[{"reaction":"🔥","users":["lunarflu","davanstrien","tomaarsen","qubvel-hf","clem","Ali-C137","AtAndDev","gabrielmbmb"],"count":8},{"reaction":"👍","users":["mikeysilva808","AtAndDev","gabrielmbmb"],"count":3}],"publishedAt":"2024-04-19T10:34:14.000Z","updatedAt":"2024-04-19T10:35:38.806Z","commentators":[],"url":"/posts/alvarobartt/840376427316230","totalUniqueImpressions":2138,"numComments":0}],"totalPosts":4,"spaces":[{"author":"alvarobartt","authorData":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","fullname":"Alvaro Bartolome","name":"alvarobartt","type":"user","isPro":false,"isHf":false},"colorFrom":"purple","colorTo":"red","createdAt":"2024-03-13T10:44:00.000Z","emoji":"🏷️","id":"alvarobartt/my-argilla","lastModified":"2024-03-13T10:44:07.000Z","likes":0,"pinned":false,"private":false,"repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"cpu-basic","requested":"cpu-basic"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"alvarobartt-my-argilla.hf.space","isCustom":false,"stage":"READY"}]},"title":"Argilla Space Template","isLikedByUser":false}],"u":{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/ZSIRRZgthYnTinV1wGE1N.jpeg","isPro":false,"fullname":"Alvaro Bartolome","user":"alvarobartt","orgs":[{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1647040810120-5f9c00a5777efc07d7f1e4be.png","fullname":"Somos NLP","name":"somosnlp","userRole":"write","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1664307416166-60420dccc15e823a685f2b03.png","fullname":"Argilla","name":"argilla","userRole":"admin","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f0c746619cb630495b814fd/j26aNEdiOgptZxJ6akGCC.png","fullname":"Hugging Face H4","name":"HuggingFaceH4","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1677518225373-5f9c00a5777efc07d7f1e4be.png","fullname":"Hackathon Somos NLP 2023: Los LLMs hablan Español","name":"somosnlp-hackathon-2023","userRole":"contributor","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f1abe7544c2adfd699860c/2lt9ePTp9MaZ2RNaDw6Ql.jpeg","fullname":"Open-Source AI Meetup","name":"SFEvent","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1622658420692-5dd96eb166059660ed1ee413.png","fullname":"Spaces-explorers","name":"spaces-explorers","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60a551a34ecc5d054c8ad93e/Ku5nM2bKq-8ZF3Jid1ocw.png","fullname":"Blog-explorers","name":"blog-explorers","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f17f0a0925b9863e28ad517/33rvDIrCmr6wpK3_W6RGz.png","fullname":"ZeroGPU Explorers","name":"zero-gpu-explorers","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/623c830997ddced06d78699b/3qTjC7d3YFCJTwpxd2noq.png","fullname":"MLX Community","name":"mlx-community","userRole":"contributor","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5f17f0a0925b9863e28ad517/nxmdd6m86cxu55UZBlQeg.jpeg","fullname":"Social Post Explorers","name":"social-post-explorers","userRole":"read","type":"org","isHf":false},{"avatarUrl":"https://www.gravatar.com/avatar/2d6237c9542237a2aaafbbafa37d583e?d=retro&size=100","fullname":"Argilla Explorers","name":"argillaexplorers","userRole":"write","type":"org","isHf":false},{"avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60420dccc15e823a685f2b03/G2lN-fPSrlswo1MDP64ok.png","fullname":"Data Is Better Together","name":"DIBT","userRole":"admin","type":"org","isHf":false},{"avatarUrl":"https://www.gravatar.com/avatar/ad82a3ef340df9782b9cda04b6b7737c?d=retro&size=100","fullname":"distilabel-internal-testing","name":"distilabel-internal-testing","userRole":"admin","type":"org","isHf":false},{"avatarUrl":"https://www.gravatar.com/avatar/846cfc2ba1b0b47e229344f8475f28df?d=retro&size=100","fullname":"ORPO Explorers","name":"orpo-explorers","userRole":"admin","type":"org","isHf":false}],"signup":{"github":"alvarobartt","twitter":"alvarobartt","details":"ml @argilla / open-source and machine learning","homepage":"https://alvarobartt.github.io/"},"isHf":false,"type":"user"},"upvotes":64,"repoFilterModels":{"sortKey":"modified"},"repoFilterDatasets":{"sortKey":"modified"},"repoFilterSpaces":{"sortKey":"modified"},"numFollowers":864,"numFollowing":40,"isFollowing":false,"isFollower":false,"sampleFollowers":[{"user":"Sachinknight19","fullname":"Sachin Knight","type":"user","isPro":false,"avatarUrl":"/avatars/c947164e9d1333e9ebded0a42a6f5ca9.svg"},{"user":"nik-dim","fullname":"Nikolaos Dimitriadis","type":"user","isPro":false,"avatarUrl":"/avatars/4cc6fe0b0a292b3f48053f7a75bf358d.svg"},{"user":"tastycode","fullname":"Sasha Devol","type":"user","isPro":false,"avatarUrl":"/avatars/c1ac1fbd4ab2daadb07aabaf1c79b3b4.svg"},{"user":"RamoseXIV","fullname":"Ramose","type":"user","isPro":false,"avatarUrl":"/avatars/aabe176e39ade58b2052d67eded68eb2.svg"}],"isWatching":false}">
🔥 Prometheus 2 was recently released by Kaist AI as an alternative and closely mirroring both human and GPT-4 evaluation, and surpassing the former Prometheus!
🌬️Fine-tuned on top of mistralai/Mistral-7B-Instruct-v0.2 and mistralai/Mixtral-8x7B-Instruct-v0.1 🗂️The datasets used for fine-tuning have been publicly released i.e. prometheus-eval/Feedback-Collection and prometheus-eval/Preference-Collection 🤝🏻Unified LM evaluator for absolute (a single prompt-completion pair) and relative (two completions for a given prompt) due to model merging ❌No longer needs a mandatory reference / golden answer, but can still be provided optionally 🔝Surpasses the former version of Prometheus, and has a high correlation with human, GPT-4, and Claude 3 Opus scores when evaluating LMs 📝Apache 2.0 license
Long-story short, an amazing job from Kaist AI bridging the gap with LLM evaluators other than proprietary and bigger models!
This week at Argilla, we decided to add a new task to use Prometheus 2 as an LLM evaluator using distilabel, so we implemented PrometheusEval.
😱 Using PrometheusEval running their 7B variant with vLLM in a single L40 on top of HuggingFaceH4/instruction-dataset, we got the 327 existing prompt-completion pairs evaluated and pushed to the Hub in less than 2 minutes!
A new synthetic preference dataset built using distilabel on top of the awesome LDJnr/Capybara from @LDJnr
The current dataset combines the already generated alternative completions from argilla/distilabel-capybara-dpo-7k-binarized, while also adding the remaining ones using the same approach!
Here are some key features on how we built it:
- 🧹 Duplicate removal, keeping the conversation besides the last assistant response, and some slight pre-processing