{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"Upstage (Solar) analysis evidence pack","description":"Public onlylabs evidence pack for cited agent analysis: captured pages, ranked public signals, and stored web-search provenance used by the background analysis workflow.","url":"https://onlylabs.fyi/labs/upstage","json_url":"https://onlylabs.fyi/analysis/upstage/evidence.json","generated_at":"2026-06-11T18:06:27.694Z","org":{"slug":"upstage","name":"Upstage (Solar)","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/upstage"},"analysis":null,"workflow":{"version":"onlylabs-deepagents-analysis-v3","provider":null,"model":null,"agent":null,"public_pack_mode":"local-pages-and-events","live_web_fetches":false,"note":"Public evidence exports do not trigger live Exa calls; stored Exa provenance is included when analysis metadata contains it."},"stats":{"pages":28,"events":78,"web":0,"evidence":88,"signal_desks":{"hiring":0,"forks":11,"releases":23,"talking":0,"repos":26},"data_radar_lanes":null,"data_radar_matches":null,"stored_analysis_evidence":null,"stored_analysis_web":null,"stored_analysis_signal_desks":null,"stored_analysis_data_radar_lanes":null,"stored_analysis_data_radar_matches":null},"stored_web_provenance":null,"evidence":[{"ref":"P1","kind":"page","title":"upstage/llama-30b-instruct model card","date":"2026-06-11T03:28:09.626127+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/llama-30b-instruct/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\ndatasets:\n- sciq\n- metaeval/ScienceQA_text_only\n- GAIR/lima\n- Open-Orca/OpenOrca\n- openbookqa\nlanguage:\n- en\ntags:\n- upstage\n- llama\n- instruct\n- instruction\npipeline_tag: text-generation\n---\n# LLaMa-30b-instruct model card\n\n## Model Details\n\n* **Developed by**: [Upstage](https://en.upstage.ai)\n* **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)\n* **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct)\n* **Language(s)**: English\n* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)\n* **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format\n* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct/discussions)\n* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)\n\n## Dataset Details\n\n### Used Datasets\n\n- [openbookqa](https://huggingface.co/datasets/openbookqa)\n- [sciq](https://huggingface.co/datasets/sciq)\n- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)\n- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)\n- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)\n- No other data was used except for the dataset mentioned above\n\n### Prompt Template\n```\n### System:\n{System}\n\n### User:\n{User}\n\n### Assistant:\n{Assistant}\n```\n\n## Usage\n\n- Tested on A100 80GB\n- Our model can handle up to 10k+ input tokens, thanks to the `rope_scalin"},{"ref":"P2","kind":"page","title":"upstage/llama-65b-instruct model card","date":"2026-06-11T03:28:09.427617+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/llama-65b-instruct/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\n\nlanguage:\n- en\ntags:\n- upstage\n- llama\n- instruct\n- instruction\npipeline_tag: text-generation\n---\n# LLaMa-65b-instruct model card\n\n## Model Details\n\n* **Developed by**: [Upstage](https://en.upstage.ai)\n* **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)\n* **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct)\n* **Language(s)**: English\n* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)\n* **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format\n* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct-2048/discussions)\n* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)\n\n## Dataset Details\n\n### Used Datasets\n\n- Orca-style dataset\n- No other data was used except for the dataset mentioned above\n\n### Prompt Template\n```\n### System:\n{System}\n\n### User:\n{User}\n\n### Assistant:\n{Assistant}\n```\n\n## Usage\n\n- Tested on A100 80GB\n- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option\n\n```python\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer\n\ntokenizer = AutoTokenizer.from_pretrained(\"upstage/llama-65b-instruct\")\nmodel = AutoModelForCausalLM.from_pretrained(\n\"upstage/llama-65b-instruct\",\ndevice_map=\"auto\",\ntorch_dtype=torch.float16,\nload_in_8bit=True,\nrope_scaling={\"type\": \"dynamic\", \"factor\": 2} # allows handling of longer inp"},{"ref":"P3","kind":"page","title":"upstage/SOLAR-0-70b-16bit model card","date":"2026-06-11T03:28:09.410417+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/SOLAR-0-70b-16bit/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlanguage:\n- en\ntags:\n- upstage\n- llama-2\n- instruct\n- instruction\npipeline_tag: text-generation\n---\n# Updates\nSolar, a new bot created by Upstage, is now available on **Poe**. As a top-ranked model on the HuggingFace Open LLM leaderboard, and a fine tune of Llama 2, Solar is a great example of the progress enabled by open source.\nTry now at https://poe.com/Solar-0-70b\n\n# SOLAR-0-70b-16bit model card\nThe model name has been changed from LLaMa-2-70b-instruct-v2 to SOLAR-0-70b-16bit\n\n## Model Details\n\n* **Developed by**: [Upstage](https://en.upstage.ai)\n* **Backbone Model**: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main)\n* **Language(s)**: English\n* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)\n* **License**: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))\n* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/Llama-2-70b-instruct-v2/discussions)\n* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)\n\n## Dataset Details\n\n### Used Datasets\n- Orca-style dataset\n- Alpaca-style dataset\n- No other dataset was used except for the dataset mentioned above\n- No benchmark test set or the training set are used\n\n### Prompt Template\n```\n### System:\n{System}\n\n### User:\n{User}\n\n### Assistant:\n{Assistant}\n```\n\n## Usage\n\n- The followings are tested on A100 80GB\n- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option\n\n```python\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer\n\ntokenizer = AutoTokenizer.from_pretrained(\"upstage/Llama-2-70b-instruct-v2\")\nmodel = AutoModelForCausalLM.from_pretrained(\n\"upstage/Llama-2-70b-instruct-v2\",\ndevice_map=\"auto\",\ntorch_dtype=torch.float16,\nload_in_8bit=True,\nrope_scaling={\"type\": \"dynamic\", \"factor\": 2} # allows handling of longer inputs\n)\n\nprompt = \"### User:\\nThomas is healthy, but he has to go to the hos"},{"ref":"P4","kind":"page","title":"upstage/Llama-2-70b-instruct model card","date":"2026-06-11T03:28:09.403051+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/Llama-2-70b-instruct/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlanguage:\n- en\ntags:\n- upstage\n- llama-2\n- instruct\n- instruction\npipeline_tag: text-generation\n---\n# LLaMa-2-70b-instruct-1024 model card\n\n## Model Details\n\n* **Developed by**: [Upstage](https://en.upstage.ai)\n* **Backbone Model**: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main)\n* **Language(s)**: English\n* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)\n* **License**: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))\n* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/Llama-2-70b-instruct/discussions)\n* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)\n\n## Dataset Details\n\n### Used Datasets\n- Orca-style dataset\n- No other data was used except for the dataset mentioned above\n\n### Prompt Template\n```\n### System:\n{System}\n\n### User:\n{User}\n\n### Assistant:\n{Assistant}\n```\n\n## Usage\n\n- Tested on A100 80GB\n- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option\n\n```python\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer\n\ntokenizer = AutoTokenizer.from_pretrained(\"upstage/Llama-2-70b-instruct\")\nmodel = AutoModelForCausalLM.from_pretrained(\n\"upstage/Llama-2-70b-instruct\",\ndevice_map=\"auto\",\ntorch_dtype=torch.float16,\nload_in_8bit=True,\nrope_scaling={\"type\": \"dynamic\", \"factor\": 2} # allows handling of longer inputs\n)\n\nprompt = \"### User:\\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\\n\\n### Assistant:\\n\"\ninputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\ndel inputs[\"token_type_ids\"]\nstreamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n\noutput = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))\noutput_text = tokenizer.decode(output[0], skip_special_tokens=True)\n```\n\n## Hardware and Software\n\n* **Hardware**: We utilized"},{"ref":"P5","kind":"page","title":"upstage/llama-30b-instruct-2048 model card","date":"2026-06-11T03:28:09.401407+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/llama-30b-instruct-2048/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\ndatasets:\n- sciq\n- metaeval/ScienceQA_text_only\n- GAIR/lima\n- Open-Orca/OpenOrca\n- openbookqa\nlanguage:\n- en\ntags:\n- upstage\n- llama\n- instruct\n- instruction\npipeline_tag: text-generation\n---\n# LLaMa-30b-instruct-2048 model card\n\n## Model Details\n\n* **Developed by**: [Upstage](https://en.upstage.ai)\n* **Backbone Model**: [LLaMA](https://github.com/facebookresearch/llama/tree/llama_v1)\n* **Variations**: It has different model parameter sizes and sequence lengths: [30B/1024](https://huggingface.co/upstage/llama-30b-instruct), [30B/2048](https://huggingface.co/upstage/llama-30b-instruct-2048), [65B/1024](https://huggingface.co/upstage/llama-65b-instruct)\n* **Language(s)**: English\n* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)\n* **License**: This model is under a **Non-commercial** Bespoke License and governed by the Meta license. You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform), but have either lost your copy of the weights or encountered issues converting them to the Transformers format\n* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/llama-30b-instruct-2048/discussions)\n* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)\n\n## Dataset Details\n\n### Used Datasets\n\n- [openbookqa](https://huggingface.co/datasets/openbookqa)\n- [sciq](https://huggingface.co/datasets/sciq)\n- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca)\n- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only)\n- [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)\n- No other data was used except for the dataset mentioned above\n\n### Prompt Template\n```\n### System:\n{System}\n\n### User:\n{User}\n\n### Assistant:\n{Assistant}\n```\n\n## Usage\n\n- Tested on A100 80GB\n- Our model can handle up to 10k+ input tokens, thanks to the `r"},{"ref":"P6","kind":"page","title":"upstage/SOLAR-10.7B-Instruct-v1.0 model card","date":"2026-06-11T03:28:09.346208+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\ndatasets:\n- c-s-ale/alpaca-gpt4-data\n- Open-Orca/OpenOrca\n- Intel/orca_dpo_pairs\n- allenai/ultrafeedback_binarized_cleaned\nlanguage:\n- en\nlicense: cc-by-nc-4.0\nbase_model:\n- upstage/SOLAR-10.7B-v1.0\n---\n\n<p align=\"left\">\n<a href=\"https://console.upstage.ai/\">\n<img src=\"https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0/resolve/main/solar-api-banner.png\" width=\"100%\"/>\n</a>\n<p>\n\n# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!**\n\n**(This model is [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) fine-tuned version for single-turn conversation.)**\n\n# **Introduction**\nWe introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.\n\nWe present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.\n\nSOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table.\nSolar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements.\n\nFor full details of this model please read our [paper](https://arxiv.org/abs/2312.15166).\n\n# **Instruction Fine-Tuning Strategy**\n\nWe utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO) [1].\n\nWe used a mixture of the following datasets\n- c-s-ale/alpaca-gpt4-data (SFT)\n- Open-Orca/OpenOrca (SFT)\n- in-house generated data utilizing Metamath [2] (SFT, DPO)\n- Intel/orca_dpo_pairs (DPO)\n- allenai/ultrafeedback_binarized_cleaned (DPO)\n\nwh"},{"ref":"P7","kind":"page","title":"upstage/TinySolar-248m-4k-code-instruct model card","date":"2026-06-11T03:28:09.13736+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-code-instruct/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\n---\n\n# Used dataset for fine-tuning\n- sahil2801/CodeAlpaca-20k\n- m-a-p/CodeFeedback-Filtered-Instruction"},{"ref":"P8","kind":"page","title":"upstage/SOLAR-10.7B-v1.0 model card","date":"2026-06-11T03:28:09.123853+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/SOLAR-10.7B-v1.0/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\n---\n\n<p align=\"left\">\n<a href=\"https://console.upstage.ai/\">\n<img src=\"https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0/resolve/main/solar-api-banner.png\" width=\"100%\"/>\n</a>\n<p>\n\n# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!**\n\n# **Introduction**\nWe introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.\n\nWe present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.\n\nSOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table.\nSolar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements ([SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)).\n\nFor full details of this model please read our [paper](https://arxiv.org/abs/2312.15166).\n\n# **Evaluation Results**\n| Model | H6 | Model Size |\n|----------------------------------------|-------|------------|\n| **SOLAR-10.7B-Instruct-v1.0** | **74.20** | **~ 11B** |\n| mistralai/Mixtral-8x7B-Instruct-v0.1 | 72.62 | ~ 46.7B |\n| 01-ai/Yi-34B-200K | 70.81 | ~ 34B |\n| 01-ai/Yi-34B | 69.42 | ~ 34B |\n| mistralai/Mixtral-8x7B-v0.1 | 68.42 | ~ 46.7B |\n| meta-llama/Llama-2-70b-hf | 67.87 | ~ 70B |\n| tiiuae/falcon-180B | 67.85 | ~ 180B |\n| **SOLAR-10.7B-v1.0** | **66.04** | **~11B** |\n| mistralai/Mistral-7B-Instruct-v0.2 | 65.71 | ~ 7B |\n| Qwen/Qwen-14B | 65.86 | ~ 14B |\n| 01-ai/Yi-34B-Chat | 65.32 | ~34B |\n| meta-llama/Llama-2-70b-chat-hf | 62.4 | ~ 70B |\n| m"},{"ref":"P9","kind":"page","title":"upstage/TinySolar-248m-4k-py-instruct model card","date":"2026-06-11T03:28:09.123492+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-py-instruct/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\n---\n\n# Used dataset for fine-tuning\n- sahil2801/CodeAlpaca-20k\n- m-a-p/CodeFeedback-Filtered-Instruction"},{"ref":"P10","kind":"page","title":"upstage/TinySolar-248m-4k-py model card","date":"2026-06-11T03:28:09.108266+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-py/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\n---"},{"ref":"P11","kind":"page","title":"upstage/TinySolar-248m-4k model card","date":"2026-06-11T03:28:09.066497+00:00","date_source":null,"source_url":"https://huggingface.co/upstage/TinySolar-248m-4k/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\n---"},{"ref":"P12","kind":"page","title":"UpstageAI/cl4kt repository metadata","date":"2026-06-11T03:20:29.542154+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/cl4kt","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/cl4kt\n\nDescription: This is our implementation for the paper \"Contrastive Learning for Knowledge Tracing\" (TheWebConf 2022).\n\nLanguage: Python\n\nStars: 31\n\nForks: 12\n\nOpen issues: 1\n\nCreated: 2022-02-02T12:09:03Z\n\nPushed: 2024-05-03T20:30:29Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Contrastive Learning for Knowledge Tracing\nThis is our implementation for the paper [Contrastive Learning for Knowledge Tracing](https://dl.acm.org/doi/abs/10.1145/3485447.3512105) (TheWebConf 2022).\n\nTo run CL4KT, please prepare the configuration file (`configs/example.yaml`) and the raw dataset (e.g., `datatset/algebra05/data.txt`, `datatset/assistments09/data.csv`, etc.).\n\nFor example, the `algebra05` dataset comes from the [KDD Cup 2010 EDM Challenge](https://pslcdatashop.web.cmu.edu/KDDCup/downloads.jsp). Datasets need to be downloaded and put inside each corresponding data folder in `dataset`.\n\nPlease use the following script to run data preprocessing:\n\n```\npython preprocess_data.py --data_name algebra05 --min_user_inter_num 5\n```\n\nPlease use the following script to run the CL4KT model:\n\n```\nCUDA_VISIBLE_DEVICES=0 python main.py --model_name cl4kt --data_name algebra05 --mask_prob 0.5 --crop_prob 0.3 --permute_prob 0.5 --replace_prob 0.5 --reg_cl 0.1\n```"},{"ref":"P13","kind":"page","title":"UpstageAI/2022-lguplus-AI-Ground repository metadata","date":"2026-06-11T03:18:05.917367+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/2022-lguplus-AI-Ground","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/2022-lguplus-AI-Ground\n\nLicense: MIT\n\nStars: 49\n\nForks: 3\n\nOpen issues: 0\n\nCreated: 2022-10-06T02:10:59Z\n\nPushed: 2022-10-17T07:45:29Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n![유플러스AI경진대회 포스터 최종본](https://user-images.githubusercontent.com/99661561/194757640-940d6dda-622c-443f-a97f-386b7559e037.png)\n\n# 2022 유플러스 AI Ground <br> 유플러스 아이들나라 콘텐츠 추천 AI 모델 개발\n\n#### 🏆 Prize <br>\n> 총 상금 1,000만원 <br>우수 참가팀은 LG 유플러스 지원시 서류 전형 및 코딩 테스트 전형 통과 혜택\n\n#### 💻 AI DATA & MODEL <br>\n> LG유플러스 아이들나라 콘텐츠 추천 데이터셋 및 베이스라인 코드 제공 <br>\n\n<br>\n\n#### 📣 AI Ground 참가자를 위한 중요한 팁! 궁금하다면 지금 바로 이 영상을 시청해주세요! <br>\n\n[![AI Ground 홍보 영상 썸네일_로고수정](https://user-images.githubusercontent.com/99661561/196115844-5e979322-3def-49c3-816d-300fb574f084.png)](https://www.youtube.com/watch?v=U96hUMFNW8A)\n\n<br>\n\n## 유플러스 AI Ground로 여러분을 초대합니다! <br>\nAI Ground는 일상을 즐겁게 바꿀 수 있는 새로운 가치, 창의적인 AI 모델을 발굴하고자 <br>\n딥러닝, 머신러닝 개발에 관심있는 누구나 참여 할 수 있는 AI 경진대회 입니다. <br> \n\n2022 유플러스 AI Ground는, 캐릭터부터 교육용 콘텐츠까지 다양한 콘텐츠를 제공하는 <br> \n**유아-아동 전용 미디어 서비스 ‘아이들나라’의 AI Task 및 실제 사용자 데이터**를 바탕으로, <br> \n**새로운 추천 아이디어 및 프로필별 맞춤형 콘텐츠 추천 AI 모델을 개발하는 AI 경진대회** 입니다. <br> \n\nAI 모델링이 익숙치 않은 분도, 쉽게 참여하실 수 있도록 **AI 경진대회 플랫폼인 ‘AI Stages’ 및 ‘베이스라인 코드’** 를 지원합니다! <br>\n베이스라인 코드를 기반으로 다양한 모델링 실험을 시도하고, <br>\n실시간 리더보드를 통해 참가자의 AI 모델 성능을 검증하며, 점진적으로 향상시킬 수 있습니다. <br> \n또한, 참여자간 토론 및 공유를 통해 창의적인 AI 추천 모델을 개발할 수 있는 AI Ground 입니다.<br>\n\n아이의 프로필 정보와 부모의 관심사 정보 그리고 시청 이력과 메타 데이터를 활용하여, <br> \n아이가 좋아하는 콘텐츠 뿐만 아니라 부모가 보여주고 싶은 콘텐츠까지 **아이들에게 더 나은 콘텐츠를 추천할 수 있는 AI 모델을 제안할 수 있는 기회입니다!** <br> \n\n우수 참가팀에게는, 총 상금 1,000만원과 <br>\nLG 유플러스 신입사원 지원시 서류 전형 및 코딩테스트 통과 혜택을 제공합니다! <br>\nAI 모델링에 관심있는 내국인이라면, 누구나 참여 가능합니다! <br>\n\n### 선 지원! 후 고민하세요!\n\n📍지원하러 가기 [2022 유플러스 AI Ground 신청서 링크](https://forms.gle/XmTo84yQT4pTQ4uNA)\n\n- 모집 기간: 2022년 10월 31일(월) 23:59 까지\n- 참가 대상: AI 모델링에 관심있는 내국인 누구나 지원 가능\n- 유의사항: 참여자 모두 개별적으로 참가 신청해주셔야 합니다. <br>\n경진대회는 개인 또는 팀(최대 3인)으로 참여 가능하며, 팀 결성을 원하시는 경우 대회 기간 중 ‘팀 결성 기간’ 내에 결성 가능합니다. <br>\nAI Stages 가입 계정을 정확히 작성하지 않을 경우, 대회 참여가 지연될 수 있습니다. <br>\n\n<br>\n<br>\n\n## AI Ground 개요\n\n### 대회 개요\n\n**주제** | LG유플러스의 아이들나라 데이터를 활용한 프로필별 맞춤형 콘텐츠 추천 AI 모델 개발\n\n**참가 대상** | 딥러닝, 머신러닝 모델링 및 개발에 관심있는 내국인 개인 또는 팀(최대 3인)\n\n**기간*"},{"ref":"P14","kind":"page","title":"UpstageAI/dataverse repository metadata","date":"2026-06-11T03:18:05.908347+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/dataverse","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/dataverse\n\nDescription: The Universe of Data. All about data, data science, and data engineering\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 564\n\nForks: 58\n\nOpen issues: 11\n\nCreated: 2023-08-21T15:50:11Z\n\nPushed: 2024-07-18T10:13:16Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n<div align=\"center\">\n\n<br>\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/images/dataverse_logo-white.png\" width=300>\n<source media=\"(prefers-color-scheme: light)\" srcset=\"docs/images/dataverse_logo-color.png\" width=300>\n<img alt=\"DATAVERSE\" src=\"docs/images/dataverse_logo-color.png\" width=300>\n</picture>\n\n<br>\n\nThe Universe of Data. \nAll about Data, Data Science, and Data Engineering. </br>\nUpstage Solar is powered by Dataverse! Try at Upstage [Console](https://console.upstage.ai/)!\n\n[Docs](https://data-verse.gitbook.io/docs/) • [Examples](https://github.com/UpstageAI/dataverse/tree/main/examples) • [API Reference](https://data-verse.readthedocs.io/en/latest/) • [FAQ](https://data-verse.gitbook.io/docs/documents/faqs) • [Contribution Guide](https://github.com/UpstageAI/dataverse/blob/main/contribution/CONTRIBUTING.md) • [Contact](mailto:dataverse@upstage.ai) • [Discord](https://discord.gg/aAqF7pyq4h) • [Paper](https://arxiv.org/abs/2403.19340)\n<br><br>\n<div align=\"left\">\n\n## Welcome to Dataverse!\nDataverse is a freely-accessible open-source project that supports your **ETL(Extract, Transform and Load) pipeline with Python**. We offer a simple, standardized and user-friendly solution for data processing and management, catering to the needs of data scientists, analysts, and developers in LLM era. Even though you don't know much about Spark, you can use it easily via _dataverse_.\n\n### With Dataverse, you are empowered to\n\n- utilize a range of preprocessing functions without the need to install multiple libraries.\n- create high-quality data for analysis and training of Large Language Models (LLM).\n- leverage Spark with ease, regardless of your expertise level.\n- facilitate smoother collaboration among users with varying degress of Spark proficiency.\n- enjoy freedom from the limitations of local environments by harnessing the capabilities of AWS"},{"ref":"P15","kind":"page","title":"UpstageAI/evalverse repository metadata","date":"2026-06-11T03:18:05.764115+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/evalverse","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/evalverse\n\nDescription: The Universe of Evaluation. All about the evaluation for LLMs.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 235\n\nForks: 25\n\nOpen issues: 10\n\nCreated: 2024-03-22T00:11:47Z\n\nPushed: 2024-07-09T19:17:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n<div align=\"center\">\n<picture>\n<source media=\"(prefers-color-scheme: dark)\" srcset=\"assets/Evalverse_White.png\" width=300>\n<source media=\"(prefers-color-scheme: light)\" srcset=\"assets/Evalverse_Color.png\" width=300>\n<img alt=\"Evalverse\" src=\"assets/Evalverse_Color.png\" width=300>\n</picture>\n\nThe Universe of Evaluation.\nAll about the evaluation for LLMs. </br>\nUpstage Solar is powered by Evalverse! Try at Upstage [Console](https://console.upstage.ai/)!\n\n[🤗HugginFace Space](https://huggingface.co/spaces/upstage/evalverse-space) • [📚Docs](https://evalverse.gitbook.io/evalverse-docs) • [📄Paper](https://arxiv.org/abs/2404.00943) \n\n[Examples](https://github.com/UpstageAI/evalverse/tree/main/examples) • [FAQ](https://evalverse.gitbook.io/evalverse-docs/documents/faqs) • [Contribution Guide](https://github.com/UpstageAI/evalverse/blob/main/contribution/CONTRIBUTING.md) • [Contact](mailto:evalverse@upstage.ai) • [Discord](https://discord.gg/D3bBj66K) \n</div>\n\n### 🚀 Newly updated\n- [2024.05.10] LLM-Evaluation Report of Evalverse is now available on [HuggingFace Space](https://huggingface.co/spaces/upstage/evalverse-space).\n\n<div align=\"center\"><img alt=\"overview\" src=\"assets/overview.png\" width=500></div>\n\n## 👋 Welcome to Evalverse!\nEvalverse is a freely accessible, open-source project designed to support your LLM (Large Language Model) evaluation needs. We provide a simple, standardized, and user-friendly solution for the processing and management of LLM evaluations, catering to the needs of AI research engineers and scientists. We also support no-code evaluation processes for people who may have less experience working with LLMs. Moreover, you will receive a well-organized report with figures summarizing the evaluation results.\n\n### With Evalverse, you are empowered to\n- access various evaluation methods without juggling multiple libraries.\n- receive insightful report about t"},{"ref":"P16","kind":"page","title":"UpstageAI/evalverse-FastChat repository metadata","date":"2026-06-11T03:18:05.60649+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/evalverse-FastChat","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/evalverse-FastChat\n\nDescription: Submodule of evalverse forked from [lm-sys/FastChat](https://github.com/lm-sys/FastChat)\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2024-03-28T03:01:38Z\n\nPushed: 2024-07-28T18:36:44Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n# FastChat\n| [**Demo**](https://chat.lmsys.org/) | [**Discord**](https://discord.gg/HSWAKCrnFx) | [**X**](https://x.com/lmsysorg) |\n\nFastChat is an open platform for training, serving, and evaluating large language model based chatbots.\n- FastChat powers Chatbot Arena (https://chat.lmsys.org/), serving over 6 million chat requests for 50+ LLMs.\n- Chatbot Arena has collected over 200K human votes from side-by-side LLM battles to compile an online [LLM Elo leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).\n\nFastChat's core features include:\n- The training and evaluation code for state-of-the-art models (e.g., Vicuna, MT-Bench).\n- A distributed multi-model serving system with web UI and OpenAI-compatible RESTful APIs.\n\n## News\n- [2023/09] 🔥 We released **LMSYS-Chat-1M**, a large-scale real-world LLM conversation dataset. Read the [report](https://arxiv.org/abs/2309.11998).\n- [2023/08] We released **Vicuna v1.5** based on Llama 2 with 4K and 16K context lengths. Download [weights](#vicuna-weights).\n- [2023/07] We released **Chatbot Arena Conversations**, a dataset containing 33k conversations with human preferences. Download it [here](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations).\n\n<details>\n<summary>More</summary>\n\n- [2023/08] We released **LongChat v1.5** based on Llama 2 with 32K context lengths. Download [weights](#longchat).\n- [2023/06] We introduced **MT-bench**, a challenging multi-turn question set for evaluating chatbots. Check out the blog [post](https://lmsys.org/blog/2023-06-22-leaderboard/).\n- [2023/06] We introduced **LongChat**, our long-context chatbots and evaluation tools. Check out the blog [post](https://lmsys.org/blog/2023-06-29-longchat/).\n- [2023/05] We introduced **Chatbot Arena** for battles among LLMs. Check out the blog [post](https://lmsys.org/blog/2023-05-03-arena).\n- [2"},{"ref":"P17","kind":"page","title":"UpstageAI/evalverse-IFEval repository metadata","date":"2026-06-11T03:18:05.260623+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/evalverse-IFEval","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/evalverse-IFEval\n\nDescription: Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/master/instruction_following_eval)\n\nLanguage: Python\n\nStars: 14\n\nForks: 4\n\nOpen issues: 2\n\nCreated: 2024-03-28T14:54:38Z\n\nPushed: 2024-05-04T01:50:27Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n# IFEval: Instruction Following Eval\n\nThis is not an officially supported Google product.\n\n## Dependencies\n\nPlease make sure that all required python packages are installed via:\n\n```\npip install -r requirements.txt\n```\n\n## How to run\n\nWe will use vLLM to generate responses for the instruction prompts via the python file `inst_eval.py`\n\n```bash\npython inst_eval.py \\\n--model {ckpt_path} --model_ref_id {model_ref_id} \\\n--output_path {ckpt_path}/eval_vllm \\\n```\n\n- ckpt_path: Path to the model checkpoints, not ending with `/`.\n- model_ref_id: A shorthand name for the model. This will be used in the path to save the evaluation results.\n\nAt the moment, you can specify `--devices` and `--gpu_per_inst_eval` to set total number of GPUs and GPUs per inst_eval process (e.g. vLLM).\nHowever, as there are slight variations with differing number of GPUs and GPUs per inst_eval process, using the default value of `--devices` and `--gpu_per_inst_eval` is recommended for reproducible evaluation results."},{"ref":"P18","kind":"page","title":"UpstageAI/evalverse-EQBench repository metadata","date":"2026-06-11T03:18:05.018959+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/evalverse-EQBench","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/evalverse-EQBench\n\nDescription: Submodule of evalverse forked from [EQ-Bench/EQ-Bench](https://github.com/EQ-bench/EQ-Bench)\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2024-05-09T08:22:25Z\n\nPushed: 2024-05-09T08:33:34Z\n\nDefault branch: main\n\nFork: no\n\nArchived: yes\n\nREADME:\n![EQ-Bench Logo](./images/eqbench_logo_sml.png)\n\n# EQ-Bench\n\nEQ-Bench is a benchmark for language models designed to assess emotional intelligence. You can read more about it in our [paper](https://arxiv.org/abs/2312.06281).\n\nThe latest leaderboard can be viewed at [EQ-Bench Leaderboard](https://eqbench.com).\n\n## News\n\n### Version 2 Released\n\nV2 of EQ-Bench contains 171 questions (compared to 60 in v1) and a new system for scoring. It is better able to discriminate performance differences between models. V2 is less subject to variance caused by perturbations (e.g. temp, sampler, quantisation, prompt format, system message). Also added is the ability to upload results to firebase.\n\nWe encourage you to move to v2, and to note which version you are using (EQ-Bench v1 or EQ-Bench v2) when publishing results to avoid confusion.\n\nNOTE: V1 scores are not directly comparable to v2 scores.\n\n<details>\n<summary>More v2 details</summary>\n\nVersion 2 of the benchmark brings three major changes:\n\n1. Increased the number of test questions from 60 to 171.\n2. Changed the scoring system from _normalised_ to _full scale_.\n3. Uploading results to firebase.\n\n### Known issues:\n\n- When using oobabooga as the inferencing engine, the api plugin stops responding after approx. 30 queries. This is handled by the benchmark pipeline by the query timing out (according to the value set in config.cfg), and then reloading ooba. The cause is unknown at this stage; the benchmark should however still complete.\n\n### Score sensitivity to perturbations\n\nOriginally 200 dialogues were generated for the test set, of which 60 of the best (most coherent & challenging) were selected for v1 of the benchmark. We had initially established very low variance between runs of the v1 benchmark, when holding all parameters the same. However it has become apparent that minor perturbations to the model "},{"ref":"P19","kind":"page","title":"UpstageAI/TFLOP repository metadata","date":"2026-06-11T03:18:05.007047+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/TFLOP","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/TFLOP\n\nDescription: Official Implementation of TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism\n\nLanguage: Python\n\nLicense: NOASSERTION\n\nStars: 51\n\nForks: 3\n\nOpen issues: 7\n\nCreated: 2024-04-22T10:48:10Z\n\nPushed: 2025-08-25T10:33:54Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism\n<strong>Official implemenetation of</strong> \"TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism\" (IJCAI 2024)\n\n![](./figures/pipeline.png)\n\n## 📣 Latest Updates\n\n- 💻 [17/01/2025] Release of TFLOP code!\n- 🚀 [15/10/2024] Try out the enterprise-grade integration of TFLOP within Upstage’s Document Parse -- [[Link](https://console.upstage.ai/playground/document-parse)]\n- ⚡️ [03/08/2024] Presentation of TFLOP in IJCAI 2024 -- [[Paper](https://arxiv.org/abs/2501.11800)]\n\n## 🚀 Getting Started\n### Installation\n```bash\n# Create a new conda environment with Python 3.9\nconda create -n tflop python=3.9\nconda activate tflop\n\n# Clone the TFLOP repository\ngit clone https://github.com/UpstageAI/TFLOP\n\n# Install required packages\ncd TFLOP\npip install torch==2.0.1 torchmetrics==1.6.0 torchvision==0.15.2\npip install -r requirements.txt\n```\n### Download required files\n1. install & login huggingface\n\nreference: https://huggingface.co/docs/huggingface_hub/en/guides/cli\n```bash\npip install -U \"huggingface_hub[cli]\"\nhuggingface-cli login\n```\n2. install git-lfs\n```bash\nsudo apt install git-lfs\ngit lfs install\n```\n3. download dataset from [huggingface](https://huggingface.co/datasets/upstage/TFLOP-dataset)\n```bash\ngit clone https://huggingface.co/datasets/upstage/TFLOP-dataset\n```\nDirectory Layout\n```bash\n├── images\n│ ├── test.tar.gz\n│ ├── train.tar.gz\n│ └── validation.tar.gz\n├── meta_data\n│ ├── erroneous_pubtabnet_data.json\n│ ├── final_eval_v2.json\n│ └── PubTabNet_2.0.0.jsonl\n└── pse_results\n├── test\n│ └── end2end_results.pkl\n├── train\n│ ├── detection_results_0.pkl\n│ ├── detection_results_1.pkl\n│ ├── detection_results_2.pkl\n│ ├── detection_results_3.pkl\n│ ├── detection_results_4.pkl\n│ ├── detection_results_5.pkl\n│ ├── detection_results_6.pkl\n│ └── detection_result"},{"ref":"P20","kind":"page","title":"UpstageAI/cookbook repository metadata","date":"2026-06-11T03:18:04.803536+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/cookbook","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/cookbook\n\nDescription: Upstage api examples and guides\n\nLanguage: Jupyter Notebook\n\nLicense: MIT\n\nStars: 197\n\nForks: 69\n\nOpen issues: 24\n\nCreated: 2024-05-21T05:45:00Z\n\nPushed: 2026-06-10T01:41:11Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Upstage Cookbook\n\nThis cookbook aims to highlight innovative use cases and outputs created by leveraging Upstage Solar and Document AI’s capabilities. We aim to inspire others by showcasing the versatility and excellence of Upstage features across various domains. The Upstage cookbook is open to the community. If you have an interesting idea for using APIs, spot a typo, or want to add or improve a guide, feel free to contribute!\n\n### How to use?\n\nGet an API key from Upstage console to try examples in the cookbook. Set the environment variable `UPSTAGE_API_KEY` with your key, or create an `.env` file with the key.\n\n### Submission Guidelines\n\n**Content:**\n\n- Source code for apps, programs, or computational projects assisted by the Upstage APIs.\n- Tutorials, educational materials, or lesson plans developed with the Upstage APIs.\n- Any other interesting applications that showcase the Upstage API's potential!\n\n**Requirements:**\n\n- Code/text entries should be in .md, .ipynb or other common formats.\n- Include an overview describing the project/output and its purpose. Provide step-by-step instructions in a logical order and Include any relevant tips, notes, or variations.\n- Projects should be original creations or properly credited if adapted from another source.\n- Submissions should not contain explicit violating content.\n\n**Rights:**\n\n- You maintain ownership and rights over your submitted project.\n- By submitting, you grant us permission to showcase and distribute the entry.\n- Entries cannot infringe on any third-party copyrights or intellectual property.\n\nLet us know if you need any other guidelines or have additional criteria to include! We’re happy to continue iterating on these submission rules.\n\nDisclaimer: The views and opinions expressed in community and partner examples do not reflect those of Upstage.\n\n### API List\n\n| API | Description | Example usage |\n| --- | --- | --- |\n| Chat | Build assistan"},{"ref":"P21","kind":"page","title":"UpstageAI/ThaiCLI_H6 repository metadata","date":"2026-06-11T03:18:04.546034+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/ThaiCLI_H6","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/ThaiCLI_H6\n\nDescription: This repository provides access to two critical benchmarks designed to advance the development and evaluation of large language models (LLMs) in Thai: ThaiCLI for evaluating cultural intelligence and Thai-H6 for assessing core language capabilities. These benchmarks are tailored for Thai\n\nStars: 7\n\nForks: 0\n\nOpen issues: 1\n\nCreated: 2024-10-07T05:59:20Z\n\nPushed: 2025-10-23T12:01:15Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# ThaiCLI and Thai-H6 Benchmarks\n### Comprehensive Benchmarks for Thai Language Models\n\nThis repository provides access to two critical benchmarks designed to advance the development and evaluation of large language models (LLMs) in Thai: **ThaiCLI** for evaluating cultural intelligence and **Thai-H6** for assessing core language capabilities. These benchmarks are tailored for Thai, an under-represented language in LLM research, to promote a deeper understanding of both linguistic and cultural nuances.\n\n**Dataset Availability**: The datasets are scheduled for release in mid-November.\n\n</br>\n\n---\n\n## 1. Introduction\nAs the significance of large language models continues to grow, there is an increasing need for evaluation frameworks that rigorously assess both language proficiency and cultural understanding—especially in languages like Thai, which are under-represented in LLM research. \n\n### Benchmarks:\n- [**ThaiCLI**](#2-thaicli) evaluates LLM performance on Thai-specific cultural intelligence tasks, offering insights into how well models can understand and respond to culturally sensitive queries.\n- [**Thai-H6**](#3-thai-h6) adapts six global benchmarks to evaluate core linguistic capabilities in Thai, providing a solid foundation for Thai LLM assessment.\n\n</br>\n\n---\n\n## 2. ThaiCLI\n### 2-1. Benchmark Overview\n![Annotation Process of ThaiCLI](assets/ThaiCLI_annotation.jpg)\nThaiCLI is specifically designed to evaluate LLMs' comprehension of cultural and societal norms in Thailand. It includes two question formats: **Factoid** and **Instruction**, across key themes such as the royal family, religion, culture, and politics.\n\n| Question Format | Theme | # of Samples |\n|------------------|-----------"},{"ref":"P22","kind":"page","title":"UpstageAI/solar-prompt-cookbook repository metadata","date":"2026-06-11T03:18:04.385477+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/solar-prompt-cookbook","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/solar-prompt-cookbook\n\nDescription: Solar Prompt Cookbook\n\nLanguage: Jupyter Notebook\n\nStars: 253\n\nForks: 67\n\nOpen issues: 2\n\nCreated: 2024-11-04T07:11:37Z\n\nPushed: 2026-02-11T14:47:56Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Solar Prompt Cookbook\n\nGetting Started Quickly with Codespace\n\n[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/studydev/Solar_Prompt_Guide?quickstart=1)\n\nPrompting serves as a cohesive natural language interface for human-AI interactions and has become widely adopted with the rise of large language models (LLMs). LLMs are particularly sensitive to prompt design. This cookbook aims to provide a comprehensive, step-by-step guide for crafting highly effective prompts within Solar, emphasizing practical techniques and strategies. Central to this course is the concept of a prompt engineering cookbook-a collection of structured recipes outlining best practices for prompt creation. These recipes present proven methods to optimize interactions with solar models, addressing common challenges and providing frameworks for diverse use cases.\n\nBy the end of this book, **you will be able to:** \n\n1. Build a strong foundation in basic prompt structure.\n2. Develop a thorough understanding of Solar’s capabilities and limitations.\n3. Discover solutions for overcoming common challenges to maximize prompt engineering with Solar.\n4. Create optimized prompts from scratch for a wide range of applications, from common use cases to industrial fields.\n\n**Some of you may wonder when to use prompt engineering versus fine-tuning.**\nHere’s a quick guide on each: \n\nUse *prompt engineering* when: \n- You need flexibility, fast iteration, and cost efficiency. \n- Tasks are general or the model is instruction-tuned.\n- Requirements may change often. \n\nUse *fine-tuning* when: \n- Tasks are speciliazed or domain-specific.\n- Consistency, accuracy, and scalability are critical.\n- Base model lacks necessary knowledge. \n\nStart with prompt engineering; move to fine-tuning if results are inconsistent or too complex to handle with prompts alone. \n\n--- \n## Course Structure and Content \n\nThis cookbook is designed t"},{"ref":"P23","kind":"page","title":"UpstageAI/mcp-upstage repository metadata","date":"2026-06-11T03:18:04.256289+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/mcp-upstage","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/mcp-upstage\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 13\n\nForks: 4\n\nOpen issues: 0\n\nCreated: 2025-04-18T01:31:18Z\n\nPushed: 2025-08-25T08:32:03Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Upstage MCP\n\n> A Model Context Protocol (MCP) server for Upstage AI's document digitization and information extraction capabilities\n\n## Overview\n\nThe Upstage MCP Server provides a robust bridge between AI assistants and Upstage AI’s powerful document processing APIs. This server enables AI models—such as Claude—to effortlessly extract and structure content from various document types including PDFs, images, and Office files. The package supports multiple formats and comes with seamless integration options for Claude Desktop.\n\n## Key Features\n\n- **Document Digitization:** Extract structured content from documents while preserving layout.\n- **Information Extraction:** Retrieve specific data points using intelligent, customizable schemas.\n- **Multi-format Support:** Handles JPEG, PNG, BMP, PDF, TIFF, HEIC, DOCX, PPTX, and XLSX.\n- **Claude Desktop Integration:** Effortlessly connect with Claude and other MCP clients.\n\n## Prerequisites\n\nBefore using this server, ensure you have the following:\n\n1. **Upstage API Key:** Obtain your API key from [Upstage API](https://console.upstage.ai/api-keys?api=document-parsing).\n2. **Python 3.10+:** The server requires Python version 3.10 or higher.\n3. The MCP server relies upon **Astral UV** to run, please [install](https://docs.astral.sh/uv/getting-started/installation/)\n\n## Installation & Configuration\n\nThis guide provides step-by-step instructions to set up and configure the mcp-upstage\n\n### Using `uv` (Recommended)\n\nNo additional installation is required when using `uvx` as it handles execution. However, if you prefer to install the package directly:\n```bash\nuv pip install mcp-upstage\n```\n\n## Configure Claude Desktop\nFor integration with Claude Desktop, add the following content to your `claude_desktop_config.json`:\n\n### Configuration Location\n\n- **Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n- **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n\n### Using uvx Command (Recommended)\n\n`"},{"ref":"P24","kind":"page","title":"UpstageAI/KIEval repository metadata","date":"2026-06-11T03:18:04.061225+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/KIEval","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/KIEval\n\nDescription: Official Implementation of KIEval: Evaluation Metric for Document Key Information Extraction\n\nLanguage: Python\n\nStars: 3\n\nForks: 1\n\nOpen issues: 4\n\nCreated: 2025-06-17T11:59:48Z\n\nPushed: 2026-01-13T20:28:24Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n## KIEval: Evaluation Metric for Document Key Information Extraction\n\nKIEval is an application-centric evaluation metric for **Document Key Information Extraction (KIE)**. \n\nThis repository contains the **official implementation** used in the paper \n**[\"KIEval: Evaluation Metric for Document Key Information Extraction\"](https://arxiv.org/abs/2503.05488)**, ICDAR 2025.\n\n---\n\n## Key characteristics\n\n- **Multi-level evaluation**: \n- **Non-group level** – entity-wise performance for standalone keys (e.g., `store_name`, `date`). \n- **Group level** – performance over **sets of related entities** (e.g., per-line item on a receipt). \n- **Structure-aware matching**: Uses strategies such as the Hungarian algorithm to align predicted and gold groups, handling **variable numbers of entities and groups**.\n- **CORD pipeline provided**: This repository ships with an end-to-end evaluation script for the **CORD** dataset via HuggingFace `datasets`.\n\n---\n\n## Evaluation flow\n- Model Output2CSV conversion stage\n- Given the model output file and the target dataset's ontology information, convert the model output into CSV files\n- Evaluation stage\n- KIEval then assesses the model's performance based on the saved pred and gt CSV files\n\n---\n## Repository structure\n\n- **`run_eval.py`**: \nHigh-level script to evaluate a model on the CORD dataset using KIEval. \n- Loads the dataset via `datasets.load_dataset`. \n- Automatically builds an ontology from CORD ground-truth. \n- Converts ground truth and predictions into CSV format. \n- Runs the KIEval metric and writes a markdown summary.\n\n- **`eval_utils.py`**: \n- `load_ontology(...)`: Derives ontology keys and grouping information from the dataset (currently supports **CORD**). \n- `parse_arguments(...)`: CLI options for `run_eval.py`. \n- `set_up_savefolder(...)`: Creates the folder structure for evaluation artifacts.\n\n- **`KIEval/kieval.py`**: \nCore imple"},{"ref":"P25","kind":"page","title":"UpstageAI/CReSt repository metadata","date":"2026-06-11T03:18:03.928838+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/CReSt","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/CReSt\n\nDescription: CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents\n\nLanguage: Python\n\nStars: 5\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-05-09T02:00:12Z\n\nPushed: 2025-07-28T07:41:46Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# CReSt Benchmark\nCReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents\n\n## ⚡️ Introduction\nCReSt is a benchmark consisting of 2,245 human-annotated examples in English and Korean, designed to capture complex, multi-step RAG scenarios.\n\nYou can explore the dataset on Hugging Face at: [https://huggingface.co/datasets/upstage/CReSt](https://huggingface.co/datasets/upstage/CReSt)\n\n## 📣 Latest Updates\n\n- [15/05/2025] Release of CReSt code\n\n## 🚀 Quick Start\n1. Clone the repository and install the required dependencies.\n\n```shell\ngit clone git@github.com:UpstageAI/CReSt.git\ncd CReSt\npip install -r requirements.txt\n```\n\n2. Copy the .env.example template and rename it to .env. Then, update it with your API keys.\n```shell\ncp .env.example .env\n``` \n\n3. Run the script.\n```shell\npython -m scripts.run_evaluation --model $MODEL \\\n--eval-model gpt-4o \\\n--method $METHOD \\\n--dataset upstage/CReSt\n```\n\n## 📜 License\nThis benchmark is distributed under the CC-by-NC 4.0.\n\n## 📝 Citation\nIf you use this code in your research, please cite:\n```\n@inproceedings{khang2025crest,\ntitle={CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents},\nauthor={Khang, Minsoo and Park, Sangjun and Hong, Teakgyu and Jung, Dawoon},\nbooktitle={TBD},\npages={TBD},\nyear={2025}\n}\n```"},{"ref":"P26","kind":"page","title":"UpstageAI/mcp-upstage-server repository metadata","date":"2026-06-11T03:18:03.711491+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/mcp-upstage-server","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/mcp-upstage-server\n\nDescription: Node.js/TypeScript MCP server for Upstage AI document processing with parsing, information extraction, schema generation, and classification tools\n\nLanguage: TypeScript\n\nStars: 2\n\nForks: 1\n\nOpen issues: 5\n\nCreated: 2025-09-03T11:00:24Z\n\nPushed: 2026-02-11T17:36:52Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# MCP-Upstage-Server\n\nNode.js/TypeScript implementation of the MCP server for Upstage AI services.\n\n## Features\n\n- **Document Parsing**: Extract structure and content from various document types (PDF, images, Office files)\n- **Information Extraction**: Extract structured information using custom or auto-generated schemas \n- **Schema Generation**: Automatically generate extraction schemas from document analysis\n- **Document Classification**: Classify documents into predefined categories (invoice, receipt, contract, etc.)\n- Built with TypeScript for type safety\n- Dual transport support: stdio (default) and HTTP Streamable\n- Async/await pattern throughout\n- Comprehensive error handling and retry logic\n- Progress reporting support\n\n## Installation\n\n### Prerequisites\n\n- Node.js 18.0.0 or higher\n- Upstage API key from [Upstage Console](https://console.upstage.ai)\n\n### Install from npm\n\n```bash\n# Install globally\nnpm install -g mcp-upstage-server\n\n# Or use with npx (no installation required)\nnpx mcp-upstage-server\n```\n\n### Install from source\n\n```bash\n# Clone the repository\ngit clone https://github.com/UpstageAI/mcp-upstage.git\ncd mcp-upstage/mcp-upstage-node\n\n# Install dependencies\nnpm install\n\n# Build the project\nnpm run build\n\n# Set up environment variables\ncp .env.example .env\n# Edit .env and add your UPSTAGE_API_KEY\n```\n\n## Usage\n\n### Running the server\n\n```bash\n# With stdio transport (default)\nUPSTAGE_API_KEY=your-api-key npx mcp-upstage-server\n\n# With HTTP Streamable transport\nUPSTAGE_API_KEY=your-api-key npx mcp-upstage-server --http\n\n# With HTTP transport on custom port\nUPSTAGE_API_KEY=your-api-key npx mcp-upstage-server --http --port 8080\n\n# Show help\nnpx mcp-upstage-server --help\n\n# Development mode (from source)\nnpm run dev\n\n# Production mode (from source)\nnpm start\n```\n\n### Integration with Claude"},{"ref":"P27","kind":"page","title":"UpstageAI/n8n-nodes-solar repository metadata","date":"2026-06-11T03:18:03.624125+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/n8n-nodes-solar","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/n8n-nodes-solar\n\nDescription: Solar LLM and Embeddings nodes for n8n workflow automation platform\n\nLanguage: TypeScript\n\nLicense: MIT\n\nStars: 0\n\nForks: 2\n\nOpen issues: 5\n\nCreated: 2025-08-23T10:02:13Z\n\nPushed: 2026-02-09T20:39:59Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# n8n-nodes-solar\n\nSolar LLM and Embeddings nodes for n8n, powered by Upstage Solar models.\n\n![Solar Node](https://img.shields.io/npm/v/n8n-nodes-solar)\n![License](https://img.shields.io/npm/l/n8n-nodes-solar)\n\n## Description\n\nThis package provides n8n community nodes for integrating with Upstage's Solar LLM and embedding models. Solar is a series of large language models that deliver exceptional performance with efficiency.\n\n## Features\n\n- **Solar Chat Model**: Use Solar LLM for chat completions with support for multiple models (solar-mini, solar-pro, solar-pro2)\n- **Solar Embeddings**: Generate high-quality embeddings using Solar embedding models\n- **Easy Authentication**: Simple API key-based authentication\n- **Multiple Input Types**: Support for single text or batch processing\n- **Comprehensive Options**: Temperature, max tokens, top-p, and more\n\n## Installation\n\n### Prerequisites\n\n- n8n version 1.0.0 or later\n- Node.js 18.0.0 or later\n\n### Install via n8n Community Nodes\n\n1. **Enable Community Nodes** (if not already enabled):\n```bash\nexport N8N_COMMUNITY_NODES_ENABLED=true\nn8n start\n```\n\n2. **Install via n8n UI**:\n- Go to **Settings** → **Community Nodes**\n- Click **Install a community node**\n- Enter: `n8n-nodes-solar`\n- Click **Install**\n\n3. **Install via npm** (alternative):\n```bash\nnpm install n8n-nodes-solar\n```\n\n## Setup\n\n### 1. Get API Key\n\n1. Sign up at [Upstage Console](https://console.upstage.ai/)\n2. Navigate to API Keys section\n3. Create a new API key\n\n### 2. Configure Credentials\n\n1. In n8n, go to **Credentials** → **Create New**\n2. Search for **\"Upstage API\"**\n3. Enter your API key\n4. Test and save\n\n## Available Nodes\n\n### Solar Chat Model\n\nUse Solar LLM models for chat completions.\n\n**Supported Models:**\n- `solar-mini` - Fast and efficient for basic tasks\n- `solar-pro` - Powerful model for complex tasks\n- `solar-pro2` - Latest and most advanced Solar "},{"ref":"P28","kind":"page","title":"UpstageAI/edu-usecase-meta-llama repository metadata","date":"2026-06-11T03:18:03.375753+00:00","date_source":null,"source_url":"https://github.com/UpstageAI/edu-usecase-meta-llama","signal_url":null,"signal_json_url":null,"text":"# UpstageAI/edu-usecase-meta-llama\n\nStars: 1\n\nForks: 14\n\nOpen issues: 1\n\nCreated: 2025-09-29T03:23:03Z\n\nPushed: 2025-10-15T06:53:58Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# 최종 프로젝트 제출 리포지토리\n\n## 개요\n\n이 리포지토리는 Meta x Llama Academy 최종 프로젝트를 제출하기 위한 공식 공간입니다.\n모든 프로젝트가 원활하게 취합될 수 있도록, 아래의 가이드라인을 반드시 준수해야 합니다.\n\n---\n\n## 프로젝트 시작 절차\n\n모든 팀은 프로젝트 시작 전, 다음 절차에 따라 팀의 작업 디렉토리를 설정해야 합니다.\n\n1. **팀 디렉토리 생성**: `projects/` 디렉토리 하위에 팀명으로 된 신규 디렉토리를 생성합니다. 디렉토리명에는 공백 대신 하이픈(-) 사용을 원칙으로 합니다.\n* `예시: projects/llama-agent-team/`\n\n2. **프로젝트 파일 관리**: 모든 소스 코드, README.md 등 프로젝트와 관련된 모든 산출물은 상기 단계에서 생성한 팀 디렉토리 내부에 위치해야 합니다(Merge Conflict 예방 차원). 각 팀은 자신만의 기술 스택과 배포 방식을 자유롭게 선택할 수 있습니다.\n\n3. **README 작성**: 각 팀의 디렉토리에는 프로젝트를 상세히 설명하는 `README.md` 파일이 반드시 포함되어야 합니다. README 작성에 필요한 필수 포함 항목은 별도 가이드를 참고해주세요.\n\n---\n\n## 디렉토리 구조 예시\n\n각 팀은 `projects/` 하위에 자신만의 디렉토리를 가지며, 팀 내부에서는 자유롭게 프로젝트 구조를 설계할 수 있습니다.\n\n### 기본 구조\n```\n.\n│\n├── README.md \n│\n└── projects/ \n│\n└── [팀명]/ # 각 팀은 자신의 팀명으로 디렉토리를 생성\n│\n├── README.md\n├── ...\n```\n\n### 예시\n\n```\nprojects/team-a/\n├── README.md\n├── requirements.txt\n├── Dockerfile \n├── .env.example\n└── src/\n├── main.py\n├── agents/\n└── services/\n```\n\n### 팀 디렉토리 내부 `README.md` 템플릿 예시\n```markdown\n# 프로젝트 이름\n---\n## 팀원 소개\n---\n## 프로젝트 개요\n---\n## 주요 기능\n---\n## 기술 스택 및 아키텍처\n### 기술 스택\n### 아키텍처\n---\n## 실행 방법\n\n## 제출 방법\n\n프로젝트 제출은 Fork & Pull Request 방식을 따릅니다.\n제출에 관한 상세 절차는 운영진이 별도로 안내한 \"최종 프로젝트 제출 가이드\" 문서를 참고해주세요.\n\n```"},{"ref":"E1","kind":"event","title":"upstage/SOLAR-10.7B-Instruct-v1.0","date":"2023-12-12T12:39:22+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0","signal_url":"https://onlylabs.fyi/signals/d66e12c7-6583-4627-9f46-fe5462b3f6b6","signal_json_url":"https://onlylabs.fyi/signals/d66e12c7-6583-4627-9f46-fe5462b3f6b6/signal.json","text":"model_released · upstage/SOLAR-10.7B-Instruct-v1.0 · signal_desk=releases · occurred_at=2023-12-12T12:39:22+00:00 · url=https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0 · hf_downloads=51949 · hf_likes=656 · hf_params=10731524096 · pipeline=text-generation · license=cc-by-nc-4.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E2","kind":"event","title":"upstage/Solar-Open-100B","date":"2025-12-10T01:10:35+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/Solar-Open-100B","signal_url":"https://onlylabs.fyi/signals/5f3e4860-16d6-403c-8200-7cdd2ec64fa8","signal_json_url":"https://onlylabs.fyi/signals/5f3e4860-16d6-403c-8200-7cdd2ec64fa8/signal.json","text":"model_released · upstage/Solar-Open-100B · signal_desk=releases · occurred_at=2025-12-10T01:10:35+00:00 · url=https://huggingface.co/upstage/Solar-Open-100B · hf_downloads=3866 · hf_likes=478 · hf_params=102651793408 · pipeline=text-generation · license=other"},{"ref":"E3","kind":"event","title":"upstage/solar-pro-preview-instruct","date":"2024-09-09T01:08:58+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro-preview-instruct","signal_url":"https://onlylabs.fyi/signals/316469cd-f4d4-49c6-8b0d-70b369c67918","signal_json_url":"https://onlylabs.fyi/signals/316469cd-f4d4-49c6-8b0d-70b369c67918/signal.json","text":"model_released · upstage/solar-pro-preview-instruct · signal_desk=releases · occurred_at=2024-09-09T01:08:58+00:00 · url=https://huggingface.co/upstage/solar-pro-preview-instruct · hf_downloads=40669 · hf_likes=457 · hf_params=22140032000 · pipeline=text-generation · license=mit"},{"ref":"E4","kind":"event","title":"upstage/SOLAR-10.7B-v1.0","date":"2023-12-12T14:57:41+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/SOLAR-10.7B-v1.0","signal_url":"https://onlylabs.fyi/signals/1db38aca-a53f-4179-b043-2e2ecef28731","signal_json_url":"https://onlylabs.fyi/signals/1db38aca-a53f-4179-b043-2e2ecef28731/signal.json","text":"model_released · upstage/SOLAR-10.7B-v1.0 · signal_desk=releases · occurred_at=2023-12-12T14:57:41+00:00 · url=https://huggingface.co/upstage/SOLAR-10.7B-v1.0 · hf_downloads=12193 · hf_likes=320 · hf_params=10731524096 · pipeline=text-generation · license=apache-2.0"},{"ref":"E5","kind":"event","title":"upstage/SOLAR-0-70b-16bit","date":"2023-07-30T01:10:53+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/SOLAR-0-70b-16bit","signal_url":"https://onlylabs.fyi/signals/30dbdd3d-4b2e-49d2-b83b-fe818eebe5b4","signal_json_url":"https://onlylabs.fyi/signals/30dbdd3d-4b2e-49d2-b83b-fe818eebe5b4/signal.json","text":"model_released · upstage/SOLAR-0-70b-16bit · signal_desk=releases · occurred_at=2023-07-30T01:10:53+00:00 · url=https://huggingface.co/upstage/SOLAR-0-70b-16bit · hf_downloads=72736 · hf_likes=259 · pipeline=text-generation"},{"ref":"E6","kind":"event","title":"upstage/llama-30b-instruct-2048","date":"2023-07-13T12:06:18+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/llama-30b-instruct-2048","signal_url":"https://onlylabs.fyi/signals/5f7e7cad-ebcc-4d87-b176-8b4696122a88","signal_json_url":"https://onlylabs.fyi/signals/5f7e7cad-ebcc-4d87-b176-8b4696122a88/signal.json","text":"model_released · upstage/llama-30b-instruct-2048 · signal_desk=releases · occurred_at=2023-07-13T12:06:18+00:00 · url=https://huggingface.co/upstage/llama-30b-instruct-2048 · hf_downloads=1506 · hf_likes=103 · pipeline=text-generation"},{"ref":"E7","kind":"event","title":"upstage/Llama-2-70b-instruct","date":"2023-07-24T09:13:08+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/Llama-2-70b-instruct","signal_url":"https://onlylabs.fyi/signals/8d1e5d50-95ca-4512-b0a3-a794275f787e","signal_json_url":"https://onlylabs.fyi/signals/8d1e5d50-95ca-4512-b0a3-a794275f787e/signal.json","text":"model_released · upstage/Llama-2-70b-instruct · signal_desk=releases · occurred_at=2023-07-24T09:13:08+00:00 · url=https://huggingface.co/upstage/Llama-2-70b-instruct · hf_downloads=2027 · hf_likes=63 · pipeline=text-generation"},{"ref":"E8","kind":"event","title":"upstage/solar-pro-preview-pretrained","date":"2024-08-29T21:29:29+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro-preview-pretrained","signal_url":"https://onlylabs.fyi/signals/abd57a06-ece0-4789-8648-a5c027fc1bd3","signal_json_url":"https://onlylabs.fyi/signals/abd57a06-ece0-4789-8648-a5c027fc1bd3/signal.json","text":"model_released · upstage/solar-pro-preview-pretrained · signal_desk=releases · occurred_at=2024-08-29T21:29:29+00:00 · url=https://huggingface.co/upstage/solar-pro-preview-pretrained · hf_likes=62 · hf_params=22140032000 · pipeline=text-generation"},{"ref":"E9","kind":"event","title":"UpstageAI/hermes-agent","date":"2026-06-08T02:36:18+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/hermes-agent","signal_url":"https://onlylabs.fyi/signals/559043f9-080e-4c7f-9629-6db81b6f7215","signal_json_url":"https://onlylabs.fyi/signals/559043f9-080e-4c7f-9629-6db81b6f7215/signal.json","text":"repo_forked · UpstageAI/hermes-agent · signal_desk=forks · occurred_at=2026-06-08T02:36:18+00:00 · url=https://github.com/UpstageAI/hermes-agent · raw={\"repo\":\"UpstageAI/hermes-agent\",\"parent\":\"NousResearch/hermes-agent\"}"},{"ref":"E10","kind":"event","title":"upstage/TinySolar-187m-4k","date":"2026-05-27T03:11:31+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-187m-4k","signal_url":"https://onlylabs.fyi/signals/d2a23d04-ba4a-4bc1-9390-4a43e15bcfaf","signal_json_url":"https://onlylabs.fyi/signals/d2a23d04-ba4a-4bc1-9390-4a43e15bcfaf/signal.json","text":"model_released · upstage/TinySolar-187m-4k · signal_desk=releases · occurred_at=2026-05-27T03:11:31+00:00 · url=https://huggingface.co/upstage/TinySolar-187m-4k · hf_downloads=78 · hf_likes=2 · hf_params=187188224 · license=apache-2.0"},{"ref":"E11","kind":"event","title":"upstage/TinySolar-111m-4k","date":"2026-05-27T03:11:21+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-111m-4k","signal_url":"https://onlylabs.fyi/signals/5b43238d-0447-4885-a3dc-64c5b43beb64","signal_json_url":"https://onlylabs.fyi/signals/5b43238d-0447-4885-a3dc-64c5b43beb64/signal.json","text":"model_released · upstage/TinySolar-111m-4k · signal_desk=releases · occurred_at=2026-05-27T03:11:21+00:00 · url=https://huggingface.co/upstage/TinySolar-111m-4k · hf_downloads=32 · hf_likes=2 · hf_params=111156224 · license=apache-2.0"},{"ref":"E12","kind":"event","title":"UpstageAI/upstage-ambassador-2nd-final-project","date":"2026-05-27T04:05:19+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/upstage-ambassador-2nd-final-project","signal_url":"https://onlylabs.fyi/signals/edc79978-c686-4eb1-9ed4-90838928c967","signal_json_url":"https://onlylabs.fyi/signals/edc79978-c686-4eb1-9ed4-90838928c967/signal.json","text":"repo_new · UpstageAI/upstage-ambassador-2nd-final-project · signal_desk=repos · occurred_at=2026-05-27T04:05:19+00:00 · url=https://github.com/UpstageAI/upstage-ambassador-2nd-final-project · raw={\"repo\":\"UpstageAI/upstage-ambassador-2nd-final-project\",\"description\":\"업스테이지 앰버서더 2기 최종 프로젝트 제출 저장소\",\"language\":\"Python\"}"},{"ref":"E13","kind":"event","title":"UpstageAI/seoul-sw-maestro-project","date":"2026-05-21T01:10:39+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/seoul-sw-maestro-project","signal_url":"https://onlylabs.fyi/signals/b8e15867-82c2-490e-ad65-8d89cd761384","signal_json_url":"https://onlylabs.fyi/signals/b8e15867-82c2-490e-ad65-8d89cd761384/signal.json","text":"repo_new · UpstageAI/seoul-sw-maestro-project · signal_desk=repos · occurred_at=2026-05-21T01:10:39+00:00 · url=https://github.com/UpstageAI/seoul-sw-maestro-project · raw={\"repo\":\"UpstageAI/seoul-sw-maestro-project\",\"description\":\"SW Maestro project submission scaffold\"}"},{"ref":"E14","kind":"event","title":"UpstageAI/busan-sw-maestro-project","date":"2026-05-21T01:10:34+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/busan-sw-maestro-project","signal_url":"https://onlylabs.fyi/signals/0dc521e0-898a-4466-ba69-f59fb98616f7","signal_json_url":"https://onlylabs.fyi/signals/0dc521e0-898a-4466-ba69-f59fb98616f7/signal.json","text":"repo_new · UpstageAI/busan-sw-maestro-project · signal_desk=repos · occurred_at=2026-05-21T01:10:34+00:00 · url=https://github.com/UpstageAI/busan-sw-maestro-project · raw={\"repo\":\"UpstageAI/busan-sw-maestro-project\",\"description\":\"SW Maestro project submission scaffold\",\"language\":\"Python\"}"},{"ref":"E15","kind":"event","title":"UpstageAI/edu-usecase-hackathon","date":"2026-05-16T04:23:18+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/edu-usecase-hackathon","signal_url":"https://onlylabs.fyi/signals/a0b1ee78-a24b-402f-a9d7-4707bac72871","signal_json_url":"https://onlylabs.fyi/signals/a0b1ee78-a24b-402f-a9d7-4707bac72871/signal.json","text":"repo_new · UpstageAI/edu-usecase-hackathon · signal_desk=repos · occurred_at=2026-05-16T04:23:18+00:00 · url=https://github.com/UpstageAI/edu-usecase-hackathon · raw={\"repo\":\"UpstageAI/edu-usecase-hackathon\",\"description\":\"해커톤 유즈케이스 \"}"},{"ref":"E16","kind":"event","title":"upstage/llama-30b-instruct","date":"2023-07-11T02:41:53+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/llama-30b-instruct","signal_url":"https://onlylabs.fyi/signals/136feb42-bed4-4ae5-9a67-3a5f91a4298e","signal_json_url":"https://onlylabs.fyi/signals/136feb42-bed4-4ae5-9a67-3a5f91a4298e/signal.json","text":"model_released · upstage/llama-30b-instruct · signal_desk=releases · occurred_at=2023-07-11T02:41:53+00:00 · url=https://huggingface.co/upstage/llama-30b-instruct · hf_downloads=1467 · hf_likes=24 · pipeline=text-generation"},{"ref":"E17","kind":"event","title":"UpstageAI/upstage-extensions-hub","date":"2026-04-20T04:21:54+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/upstage-extensions-hub","signal_url":"https://onlylabs.fyi/signals/becf30e8-6640-4619-bf99-abfee14e2952","signal_json_url":"https://onlylabs.fyi/signals/becf30e8-6640-4619-bf99-abfee14e2952/signal.json","text":"repo_new · UpstageAI/upstage-extensions-hub · signal_desk=repos · occurred_at=2026-04-20T04:21:54+00:00 · url=https://github.com/UpstageAI/upstage-extensions-hub · stars=9 · raw={\"repo\":\"UpstageAI/upstage-extensions-hub\",\"language\":\"Shell\"}"},{"ref":"E18","kind":"event","title":"upstage/llama-65b-instruct","date":"2023-07-17T12:24:11+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/llama-65b-instruct","signal_url":"https://onlylabs.fyi/signals/f70add8e-3e66-4a7c-b597-a8a7e5412626","signal_json_url":"https://onlylabs.fyi/signals/f70add8e-3e66-4a7c-b597-a8a7e5412626/signal.json","text":"model_released · upstage/llama-65b-instruct · signal_desk=releases · occurred_at=2023-07-17T12:24:11+00:00 · url=https://huggingface.co/upstage/llama-65b-instruct · hf_downloads=1465 · hf_likes=15 · pipeline=text-generation"},{"ref":"E19","kind":"event","title":"upstage/solar-1-mini-tokenizer","date":"2024-05-02T06:26:22+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-1-mini-tokenizer","signal_url":"https://onlylabs.fyi/signals/f3f2f097-6a68-4a37-9d4e-1731f4ed959f","signal_json_url":"https://onlylabs.fyi/signals/f3f2f097-6a68-4a37-9d4e-1731f4ed959f/signal.json","text":"model_released · upstage/solar-1-mini-tokenizer · signal_desk=releases · occurred_at=2024-05-02T06:26:22+00:00 · url=https://huggingface.co/upstage/solar-1-mini-tokenizer · hf_likes=14 · license=apache-2.0"},{"ref":"E20","kind":"event","title":"upstage/TinySolar-248m-4k","date":"2024-02-07T14:49:15+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-248m-4k","signal_url":"https://onlylabs.fyi/signals/e97e6ef2-0a31-4a16-a011-d5cb795b3415","signal_json_url":"https://onlylabs.fyi/signals/e97e6ef2-0a31-4a16-a011-d5cb795b3415/signal.json","text":"model_released · upstage/TinySolar-248m-4k · signal_desk=releases · occurred_at=2024-02-07T14:49:15+00:00 · url=https://huggingface.co/upstage/TinySolar-248m-4k · hf_downloads=225 · hf_likes=12 · hf_params=248013824 · pipeline=text-generation · license=apache-2.0"},{"ref":"E21","kind":"event","title":"upstage/solar-pro-preview-tokenizer","date":"2024-09-04T01:59:07+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro-preview-tokenizer","signal_url":"https://onlylabs.fyi/signals/ba21775f-e133-47f1-bd4e-6cd41b7eec06","signal_json_url":"https://onlylabs.fyi/signals/ba21775f-e133-47f1-bd4e-6cd41b7eec06/signal.json","text":"model_released · upstage/solar-pro-preview-tokenizer · signal_desk=releases · occurred_at=2024-09-04T01:59:07+00:00 · url=https://huggingface.co/upstage/solar-pro-preview-tokenizer · hf_likes=12 · license=apache-2.0"},{"ref":"E22","kind":"event","title":"UpstageAI/security-audit","date":"2026-04-01T03:36:08+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/security-audit","signal_url":"https://onlylabs.fyi/signals/c05b141b-94ce-43d5-bf49-dd6edf776053","signal_json_url":"https://onlylabs.fyi/signals/c05b141b-94ce-43d5-bf49-dd6edf776053/signal.json","text":"repo_new · UpstageAI/security-audit · signal_desk=repos · occurred_at=2026-04-01T03:36:08+00:00 · url=https://github.com/UpstageAI/security-audit · raw={\"repo\":\"UpstageAI/security-audit\",\"description\":\"Public\",\"language\":\"Shell\"}"},{"ref":"E23","kind":"event","title":"upstage/TinySolar-248m-4k-code-instruct","date":"2024-04-15T02:21:14+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-code-instruct","signal_url":"https://onlylabs.fyi/signals/26fd98a4-8ec3-464b-a92b-edf69639afe3","signal_json_url":"https://onlylabs.fyi/signals/26fd98a4-8ec3-464b-a92b-edf69639afe3/signal.json","text":"model_released · upstage/TinySolar-248m-4k-code-instruct · signal_desk=releases · occurred_at=2024-04-15T02:21:14+00:00 · url=https://huggingface.co/upstage/TinySolar-248m-4k-code-instruct · hf_downloads=120 · hf_likes=9 · hf_params=248013824 · pipeline=text-generation · license=apache-2.0"},{"ref":"E24","kind":"event","title":"upstage/solar-docvision-preview-tokenizer","date":"2024-09-04T07:15:35+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-docvision-preview-tokenizer","signal_url":"https://onlylabs.fyi/signals/5301dbb0-9552-4f38-a58f-6bd2d2e92f23","signal_json_url":"https://onlylabs.fyi/signals/5301dbb0-9552-4f38-a58f-6bd2d2e92f23/signal.json","text":"model_released · upstage/solar-docvision-preview-tokenizer · signal_desk=releases · occurred_at=2024-09-04T07:15:35+00:00 · url=https://huggingface.co/upstage/solar-docvision-preview-tokenizer · hf_likes=7 · license=apache-2.0"},{"ref":"E25","kind":"event","title":"upstage/TinySolar-248m-4k-py","date":"2024-02-07T03:33:41+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-py","signal_url":"https://onlylabs.fyi/signals/d4cb7cc4-ead9-457e-8f2d-43839c05f158","signal_json_url":"https://onlylabs.fyi/signals/d4cb7cc4-ead9-457e-8f2d-43839c05f158/signal.json","text":"model_released · upstage/TinySolar-248m-4k-py · signal_desk=releases · occurred_at=2024-02-07T03:33:41+00:00 · url=https://huggingface.co/upstage/TinySolar-248m-4k-py · hf_downloads=136 · hf_likes=5 · hf_params=248013824 · pipeline=text-generation · license=apache-2.0"},{"ref":"E26","kind":"event","title":"upstage/solar-pro-tokenizer","date":"2024-11-15T05:14:07+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro-tokenizer","signal_url":"https://onlylabs.fyi/signals/e279a0c1-088d-4e02-8eff-513937482b5d","signal_json_url":"https://onlylabs.fyi/signals/e279a0c1-088d-4e02-8eff-513937482b5d/signal.json","text":"model_released · upstage/solar-pro-tokenizer · signal_desk=releases · occurred_at=2024-11-15T05:14:07+00:00 · url=https://huggingface.co/upstage/solar-pro-tokenizer · hf_likes=4 · license=apache-2.0"},{"ref":"E27","kind":"event","title":"UpstageAI/dataverse","date":"2023-08-21T15:50:11+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/dataverse","signal_url":"https://onlylabs.fyi/signals/836c47a0-11aa-4634-8493-a4f24384087b","signal_json_url":"https://onlylabs.fyi/signals/836c47a0-11aa-4634-8493-a4f24384087b/signal.json","text":"repo_new · UpstageAI/dataverse · signal_desk=repos · occurred_at=2023-08-21T15:50:11+00:00 · url=https://github.com/UpstageAI/dataverse · stars=564 · raw={\"repo\":\"UpstageAI/dataverse\",\"description\":\"The Universe of Data. All about data, data science, and data engineering\",\"language\":\"Python\"}"},{"ref":"E28","kind":"event","title":"upstage/TinySolar-248m-4k-py-instruct","date":"2024-04-11T08:33:20+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TinySolar-248m-4k-py-instruct","signal_url":"https://onlylabs.fyi/signals/d24f783d-ff2c-491e-9904-7f11d6cbdb26","signal_json_url":"https://onlylabs.fyi/signals/d24f783d-ff2c-491e-9904-7f11d6cbdb26/signal.json","text":"model_released · upstage/TinySolar-248m-4k-py-instruct · signal_desk=releases · occurred_at=2024-04-11T08:33:20+00:00 · url=https://huggingface.co/upstage/TinySolar-248m-4k-py-instruct · hf_downloads=79 · hf_likes=2 · hf_params=248013824 · pipeline=text-generation · license=apache-2.0"},{"ref":"E29","kind":"event","title":"upstage/TFLOP","date":"2025-11-06T06:45:38+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/TFLOP","signal_url":"https://onlylabs.fyi/signals/f3a6e949-4181-448d-9d4e-90d73ddc5fd4","signal_json_url":"https://onlylabs.fyi/signals/f3a6e949-4181-448d-9d4e-90d73ddc5fd4/signal.json","text":"model_released · upstage/TFLOP · signal_desk=releases · occurred_at=2025-11-06T06:45:38+00:00 · url=https://huggingface.co/upstage/TFLOP · hf_downloads=27 · hf_likes=2 · license=cc-by-nc-4.0"},{"ref":"E30","kind":"event","title":"upstage/solar-pro3-tokenizer","date":"2026-01-23T08:41:27+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro3-tokenizer","signal_url":"https://onlylabs.fyi/signals/39369cc6-2acb-4c22-a023-8aacde9721df","signal_json_url":"https://onlylabs.fyi/signals/39369cc6-2acb-4c22-a023-8aacde9721df/signal.json","text":"model_released · upstage/solar-pro3-tokenizer · signal_desk=releases · occurred_at=2026-01-23T08:41:27+00:00 · url=https://huggingface.co/upstage/solar-pro3-tokenizer · hf_likes=2 · license=other"},{"ref":"E31","kind":"event","title":"UpstageAI/sw-maestro-project","date":"2026-03-17T07:23:04+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/sw-maestro-project","signal_url":"https://onlylabs.fyi/signals/7c0f9017-c9ea-406a-a488-4f98771cdca1","signal_json_url":"https://onlylabs.fyi/signals/7c0f9017-c9ea-406a-a488-4f98771cdca1/signal.json","text":"repo_new · UpstageAI/sw-maestro-project · signal_desk=repos · occurred_at=2026-03-17T07:23:04+00:00 · url=https://github.com/UpstageAI/sw-maestro-project · raw={\"repo\":\"UpstageAI/sw-maestro-project\",\"language\":\"HTML\"}"},{"ref":"E32","kind":"event","title":"UpstageAI/solar-prompt-cookbook","date":"2024-11-04T07:11:37+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/solar-prompt-cookbook","signal_url":"https://onlylabs.fyi/signals/df0c2aa9-f2d3-4491-a944-a4f17f551e3e","signal_json_url":"https://onlylabs.fyi/signals/df0c2aa9-f2d3-4491-a944-a4f17f551e3e/signal.json","text":"repo_new · UpstageAI/solar-prompt-cookbook · signal_desk=repos · occurred_at=2024-11-04T07:11:37+00:00 · url=https://github.com/UpstageAI/solar-prompt-cookbook · stars=253 · raw={\"repo\":\"UpstageAI/solar-prompt-cookbook\",\"description\":\"Solar Prompt Cookbook\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E33","kind":"event","title":"UpstageAI/evalverse","date":"2024-03-22T00:11:47+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/evalverse","signal_url":"https://onlylabs.fyi/signals/1c5c1920-1c1d-42bb-b74f-ef7881e10a42","signal_json_url":"https://onlylabs.fyi/signals/1c5c1920-1c1d-42bb-b74f-ef7881e10a42/signal.json","text":"repo_new · UpstageAI/evalverse · signal_desk=repos · occurred_at=2024-03-22T00:11:47+00:00 · url=https://github.com/UpstageAI/evalverse · stars=235 · raw={\"repo\":\"UpstageAI/evalverse\",\"description\":\"The Universe of Evaluation. All about the evaluation for LLMs.\",\"language\":\"Python\"}"},{"ref":"E34","kind":"event","title":"upstage/solar-pro2-tokenizer","date":"2025-07-08T03:31:42+00:00","date_source":"source","source_url":"https://huggingface.co/upstage/solar-pro2-tokenizer","signal_url":"https://onlylabs.fyi/signals/06fc6466-0696-4f42-a8ce-1c0f491e979e","signal_json_url":"https://onlylabs.fyi/signals/06fc6466-0696-4f42-a8ce-1c0f491e979e/signal.json","text":"model_released · upstage/solar-pro2-tokenizer · signal_desk=releases · occurred_at=2025-07-08T03:31:42+00:00 · url=https://huggingface.co/upstage/solar-pro2-tokenizer · hf_likes=1 · license=other"},{"ref":"E35","kind":"event","title":"UpstageAI/cookbook","date":"2024-05-21T05:45:00+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/cookbook","signal_url":"https://onlylabs.fyi/signals/fff2fefc-6b1f-47fd-9a51-0cea477f89e2","signal_json_url":"https://onlylabs.fyi/signals/fff2fefc-6b1f-47fd-9a51-0cea477f89e2/signal.json","text":"repo_new · UpstageAI/cookbook · signal_desk=repos · occurred_at=2024-05-21T05:45:00+00:00 · url=https://github.com/UpstageAI/cookbook · stars=198 · raw={\"repo\":\"UpstageAI/cookbook\",\"description\":\"Upstage api examples and guides\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E36","kind":"event","title":"UpstageAI/TFLOP","date":"2024-04-22T10:48:10+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/TFLOP","signal_url":"https://onlylabs.fyi/signals/4007f7eb-97e5-4e4f-967a-19bfb7eaa61a","signal_json_url":"https://onlylabs.fyi/signals/4007f7eb-97e5-4e4f-967a-19bfb7eaa61a/signal.json","text":"repo_new · UpstageAI/TFLOP · signal_desk=repos · occurred_at=2024-04-22T10:48:10+00:00 · url=https://github.com/UpstageAI/TFLOP · stars=51 · raw={\"repo\":\"UpstageAI/TFLOP\",\"description\":\"Official Implementation of TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism\",\"language\":\"Python\"}"},{"ref":"E37","kind":"event","title":"UpstageAI/2022-lguplus-AI-Ground","date":"2022-10-06T02:10:59+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/2022-lguplus-AI-Ground","signal_url":"https://onlylabs.fyi/signals/5ccfefa8-ceb9-475c-a91b-48602e23e1dc","signal_json_url":"https://onlylabs.fyi/signals/5ccfefa8-ceb9-475c-a91b-48602e23e1dc/signal.json","text":"repo_new · UpstageAI/2022-lguplus-AI-Ground · signal_desk=repos · occurred_at=2022-10-06T02:10:59+00:00 · url=https://github.com/UpstageAI/2022-lguplus-AI-Ground · stars=49 · raw={\"repo\":\"UpstageAI/2022-lguplus-AI-Ground\"}"},{"ref":"E38","kind":"event","title":"UpstageAI/cl4kt","date":"2022-02-02T12:09:03+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/cl4kt","signal_url":"https://onlylabs.fyi/signals/7856e4cc-725b-4e25-be06-394210d5a7ef","signal_json_url":"https://onlylabs.fyi/signals/7856e4cc-725b-4e25-be06-394210d5a7ef/signal.json","text":"repo_new · UpstageAI/cl4kt · signal_desk=repos · occurred_at=2022-02-02T12:09:03+00:00 · url=https://github.com/UpstageAI/cl4kt · stars=31 · raw={\"repo\":\"UpstageAI/cl4kt\",\"description\":\"This is our implementation for the paper \\\"Contrastive Learning for Knowledge Tracing\\\" (TheWebConf 2022).\",\"language\":\"Python\"}"},{"ref":"E39","kind":"event","title":"UpstageAI/evalverse-IFEval","date":"2024-03-28T14:54:38+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/evalverse-IFEval","signal_url":"https://onlylabs.fyi/signals/fd15d7f4-a93f-47c8-8b47-ef2862e7b9bf","signal_json_url":"https://onlylabs.fyi/signals/fd15d7f4-a93f-47c8-8b47-ef2862e7b9bf/signal.json","text":"repo_new · UpstageAI/evalverse-IFEval · signal_desk=repos · occurred_at=2024-03-28T14:54:38+00:00 · url=https://github.com/UpstageAI/evalverse-IFEval · stars=14 · raw={\"repo\":\"UpstageAI/evalverse-IFEval\",\"description\":\"Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/master/instruction_following_eval)\",\"language\":\"Python\"}"},{"ref":"E40","kind":"event","title":"UpstageAI/mcp-upstage","date":"2025-04-18T01:31:18+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/mcp-upstage","signal_url":"https://onlylabs.fyi/signals/c6d15613-a6b3-47e8-8ade-8d1b2b808a6e","signal_json_url":"https://onlylabs.fyi/signals/c6d15613-a6b3-47e8-8ade-8d1b2b808a6e/signal.json","text":"repo_new · UpstageAI/mcp-upstage · signal_desk=repos · occurred_at=2025-04-18T01:31:18+00:00 · url=https://github.com/UpstageAI/mcp-upstage · stars=13 · raw={\"repo\":\"UpstageAI/mcp-upstage\",\"language\":\"Python\"}"},{"ref":"E41","kind":"event","title":"UpstageAI/ThaiCLI_H6","date":"2024-10-07T05:59:20+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/ThaiCLI_H6","signal_url":"https://onlylabs.fyi/signals/b8eb3013-258e-4114-a402-5452b485509b","signal_json_url":"https://onlylabs.fyi/signals/b8eb3013-258e-4114-a402-5452b485509b/signal.json","text":"repo_new · UpstageAI/ThaiCLI_H6 · signal_desk=repos · occurred_at=2024-10-07T05:59:20+00:00 · url=https://github.com/UpstageAI/ThaiCLI_H6 · stars=7 · raw={\"repo\":\"UpstageAI/ThaiCLI_H6\",\"description\":\"This repository provides access to two critical benchmarks designed to advance the development and evaluation of large language models (LLMs) in Thai: ThaiCLI for evaluating cultural intelligence and Thai-H6 for assessing core language capabilities. These benchmarks are tailored for Thai\"}"},{"ref":"E42","kind":"event","title":"UpstageAI/CReSt","date":"2025-05-09T02:00:12+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/CReSt","signal_url":"https://onlylabs.fyi/signals/106d5c20-346c-4e4c-86eb-f5480bf62a28","signal_json_url":"https://onlylabs.fyi/signals/106d5c20-346c-4e4c-86eb-f5480bf62a28/signal.json","text":"repo_new · UpstageAI/CReSt · signal_desk=repos · occurred_at=2025-05-09T02:00:12+00:00 · url=https://github.com/UpstageAI/CReSt · stars=5 · raw={\"repo\":\"UpstageAI/CReSt\",\"description\":\"CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents\",\"language\":\"Python\"}"},{"ref":"E43","kind":"event","title":"UpstageAI/upstage-open-chat","date":"2025-04-08T22:09:24+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/upstage-open-chat","signal_url":"https://onlylabs.fyi/signals/9aaf9d88-7460-4687-95cf-8519e5cbb887","signal_json_url":"https://onlylabs.fyi/signals/9aaf9d88-7460-4687-95cf-8519e5cbb887/signal.json","text":"repo_forked · UpstageAI/upstage-open-chat · signal_desk=forks · occurred_at=2025-04-08T22:09:24+00:00 · url=https://github.com/UpstageAI/upstage-open-chat · stars=4 · raw={\"repo\":\"UpstageAI/upstage-open-chat\",\"parent\":\"open-webui/open-webui\"}"},{"ref":"E44","kind":"event","title":"UpstageAI/KIEval","date":"2025-06-17T11:59:48+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/KIEval","signal_url":"https://onlylabs.fyi/signals/91619b1f-fa26-4c2a-be56-5399b8b2c45d","signal_json_url":"https://onlylabs.fyi/signals/91619b1f-fa26-4c2a-be56-5399b8b2c45d/signal.json","text":"repo_new · UpstageAI/KIEval · signal_desk=repos · occurred_at=2025-06-17T11:59:48+00:00 · url=https://github.com/UpstageAI/KIEval · stars=3 · raw={\"repo\":\"UpstageAI/KIEval\",\"description\":\"Official Implementation of KIEval: Evaluation Metric for Document Key Information Extraction\",\"language\":\"Python\"}"},{"ref":"E45","kind":"event","title":"UpstageAI/mcp-upstage-server","date":"2025-09-03T11:00:24+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/mcp-upstage-server","signal_url":"https://onlylabs.fyi/signals/3d2b29e1-e343-47de-896a-d527c5bf72db","signal_json_url":"https://onlylabs.fyi/signals/3d2b29e1-e343-47de-896a-d527c5bf72db/signal.json","text":"repo_new · UpstageAI/mcp-upstage-server · signal_desk=repos · occurred_at=2025-09-03T11:00:24+00:00 · url=https://github.com/UpstageAI/mcp-upstage-server · stars=2 · raw={\"repo\":\"UpstageAI/mcp-upstage-server\",\"description\":\"Node.js/TypeScript MCP server for Upstage AI document processing with parsing, information extraction, schema generation, and classification tools\",\"language\":\"TypeScript\"}"},{"ref":"E46","kind":"event","title":"UpstageAI/vllm","date":"2025-12-29T06:50:24+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/vllm","signal_url":"https://onlylabs.fyi/signals/176d8916-1297-4814-bdbc-81b010962da6","signal_json_url":"https://onlylabs.fyi/signals/176d8916-1297-4814-bdbc-81b010962da6/signal.json","text":"repo_forked · UpstageAI/vllm · signal_desk=forks · occurred_at=2025-12-29T06:50:24+00:00 · url=https://github.com/UpstageAI/vllm · stars=1 · raw={\"repo\":\"UpstageAI/vllm\",\"parent\":\"vllm-project/vllm\"}"},{"ref":"E47","kind":"event","title":"UpstageAI/n8n-nodes-upstage","date":"2025-10-26T00:31:50+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/n8n-nodes-upstage","signal_url":"https://onlylabs.fyi/signals/6e0435a6-341e-4c50-a04e-5637bd3e6b30","signal_json_url":"https://onlylabs.fyi/signals/6e0435a6-341e-4c50-a04e-5637bd3e6b30/signal.json","text":"repo_new · UpstageAI/n8n-nodes-upstage · signal_desk=repos · occurred_at=2025-10-26T00:31:50+00:00 · url=https://github.com/UpstageAI/n8n-nodes-upstage · stars=1 · raw={\"repo\":\"UpstageAI/n8n-nodes-upstage\",\"description\":\"Upstage LLM and Embeddings nodes for n8n\",\"language\":\"TypeScript\"}"},{"ref":"E48","kind":"event","title":"UpstageAI/GEC-Promptathon","date":"2025-10-21T06:51:46+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/GEC-Promptathon","signal_url":"https://onlylabs.fyi/signals/5ba6eb7e-f18f-4d87-9939-72eb6363ce1f","signal_json_url":"https://onlylabs.fyi/signals/5ba6eb7e-f18f-4d87-9939-72eb6363ce1f/signal.json","text":"repo_new · UpstageAI/GEC-Promptathon · signal_desk=repos · occurred_at=2025-10-21T06:51:46+00:00 · url=https://github.com/UpstageAI/GEC-Promptathon · stars=1 · raw={\"repo\":\"UpstageAI/GEC-Promptathon\",\"description\":\"Fastcampus Kernel Academy AI 수강생들과 진행한 Grammar Error Correction Promphaton\"}"},{"ref":"E49","kind":"event","title":"UpstageAI/edu-usecase-meta-llama","date":"2025-09-29T03:23:03+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/edu-usecase-meta-llama","signal_url":"https://onlylabs.fyi/signals/13e7383c-d567-45b6-b355-dc5d94497d79","signal_json_url":"https://onlylabs.fyi/signals/13e7383c-d567-45b6-b355-dc5d94497d79/signal.json","text":"repo_new · UpstageAI/edu-usecase-meta-llama · signal_desk=repos · occurred_at=2025-09-29T03:23:03+00:00 · url=https://github.com/UpstageAI/edu-usecase-meta-llama · stars=1 · raw={\"repo\":\"UpstageAI/edu-usecase-meta-llama\"}"},{"ref":"E50","kind":"event","title":"UpstageAI/gpushare-scheduler-extender","date":"2025-01-31T01:21:54+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/gpushare-scheduler-extender","signal_url":"https://onlylabs.fyi/signals/3da798ae-8ce7-481b-9b2d-68a3b9ba82ea","signal_json_url":"https://onlylabs.fyi/signals/3da798ae-8ce7-481b-9b2d-68a3b9ba82ea/signal.json","text":"repo_forked · UpstageAI/gpushare-scheduler-extender · signal_desk=forks · occurred_at=2025-01-31T01:21:54+00:00 · url=https://github.com/UpstageAI/gpushare-scheduler-extender · stars=1 · raw={\"repo\":\"UpstageAI/gpushare-scheduler-extender\",\"parent\":\"AliyunContainerService/gpushare-scheduler-extender\"}"},{"ref":"E51","kind":"event","title":"UpstageAI/eduteam-ai-edu-day","date":"2026-02-25T11:25:21+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/eduteam-ai-edu-day","signal_url":"https://onlylabs.fyi/signals/37f3da1b-98f9-421e-b83d-f40bcd993749","signal_json_url":"https://onlylabs.fyi/signals/37f3da1b-98f9-421e-b83d-f40bcd993749/signal.json","text":"repo_new · UpstageAI/eduteam-ai-edu-day · signal_desk=repos · occurred_at=2026-02-25T11:25:21+00:00 · url=https://github.com/UpstageAI/eduteam-ai-edu-day · raw={\"repo\":\"UpstageAI/eduteam-ai-edu-day\",\"language\":\"JavaScript\"}"},{"ref":"E52","kind":"event","title":"UpstageAI/opencode","date":"2026-02-22T20:57:19+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/opencode","signal_url":"https://onlylabs.fyi/signals/df5240f5-a7c7-4253-85e9-512bcba041d9","signal_json_url":"https://onlylabs.fyi/signals/df5240f5-a7c7-4253-85e9-512bcba041d9/signal.json","text":"repo_forked · UpstageAI/opencode · signal_desk=forks · occurred_at=2026-02-22T20:57:19+00:00 · url=https://github.com/UpstageAI/opencode · raw={\"repo\":\"UpstageAI/opencode\",\"parent\":\"anomalyco/opencode\"}"},{"ref":"E53","kind":"event","title":"UpstageAI/edu-usecase-sesac-product-engineering-project","date":"2026-02-06T02:58:03+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/edu-usecase-sesac-product-engineering-project","signal_url":"https://onlylabs.fyi/signals/e99cfe40-8425-4073-abf2-384aa7e60fa9","signal_json_url":"https://onlylabs.fyi/signals/e99cfe40-8425-4073-abf2-384aa7e60fa9/signal.json","text":"repo_new · UpstageAI/edu-usecase-sesac-product-engineering-project · signal_desk=repos · occurred_at=2026-02-06T02:58:03+00:00 · url=https://github.com/UpstageAI/edu-usecase-sesac-product-engineering-project · raw={\"repo\":\"UpstageAI/edu-usecase-sesac-product-engineering-project\",\"description\":\"SeSAC 교육과정 중 Product Engineering Project를 위한 레포지토리입니다.\",\"language\":\"Python\"}"},{"ref":"E54","kind":"event","title":"UpstageAI/Gym","date":"2026-01-31T02:52:48+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/Gym","signal_url":"https://onlylabs.fyi/signals/96714acf-bfc6-4f25-ad4d-dcb3e019eaae","signal_json_url":"https://onlylabs.fyi/signals/96714acf-bfc6-4f25-ad4d-dcb3e019eaae/signal.json","text":"repo_forked · UpstageAI/Gym · signal_desk=forks · occurred_at=2026-01-31T02:52:48+00:00 · url=https://github.com/UpstageAI/Gym · raw={\"repo\":\"UpstageAI/Gym\",\"parent\":\"NVIDIA-NeMo/Gym\"}"},{"ref":"E55","kind":"event","title":"UpstageAI/transformers","date":"2026-01-09T02:49:16+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/transformers","signal_url":"https://onlylabs.fyi/signals/00a08825-977b-40e9-86f7-9d88226a2434","signal_json_url":"https://onlylabs.fyi/signals/00a08825-977b-40e9-86f7-9d88226a2434/signal.json","text":"repo_forked · UpstageAI/transformers · signal_desk=forks · occurred_at=2026-01-09T02:49:16+00:00 · url=https://github.com/UpstageAI/transformers · raw={\"repo\":\"UpstageAI/transformers\",\"parent\":\"huggingface/transformers\"}"},{"ref":"E56","kind":"event","title":"UpstageAI/solar-open","date":"2025-12-17T00:48:44+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/solar-open","signal_url":"https://onlylabs.fyi/signals/7fd82930-5175-4a30-81fe-c27132d512f3","signal_json_url":"https://onlylabs.fyi/signals/7fd82930-5175-4a30-81fe-c27132d512f3/signal.json","text":"repo_new · UpstageAI/solar-open · signal_desk=repos · occurred_at=2025-12-17T00:48:44+00:00 · url=https://github.com/UpstageAI/solar-open · raw={\"repo\":\"UpstageAI/solar-open\"}"},{"ref":"E57","kind":"event","title":"UpstageAI/tau2-bench","date":"2025-08-07T05:50:18+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/tau2-bench","signal_url":"https://onlylabs.fyi/signals/8a7d4f11-8520-44a7-94c7-2f6a61bb7e34","signal_json_url":"https://onlylabs.fyi/signals/8a7d4f11-8520-44a7-94c7-2f6a61bb7e34/signal.json","text":"repo_forked · UpstageAI/tau2-bench · signal_desk=forks · occurred_at=2025-08-07T05:50:18+00:00 · url=https://github.com/UpstageAI/tau2-bench · raw={\"repo\":\"UpstageAI/tau2-bench\",\"parent\":\"sierra-research/tau2-bench\"}"},{"ref":"E58","kind":"event","title":"UpstageAI/upstage-open-chat-test","date":"2025-07-03T11:25:10+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/upstage-open-chat-test","signal_url":"https://onlylabs.fyi/signals/f1eed0b6-d608-40c1-b7c4-8d265c81ae53","signal_json_url":"https://onlylabs.fyi/signals/f1eed0b6-d608-40c1-b7c4-8d265c81ae53/signal.json","text":"repo_forked · UpstageAI/upstage-open-chat-test · signal_desk=forks · occurred_at=2025-07-03T11:25:10+00:00 · url=https://github.com/UpstageAI/upstage-open-chat-test · raw={\"repo\":\"UpstageAI/upstage-open-chat-test\",\"parent\":\"UpstageAI/upstage-open-chat\"}"},{"ref":"E59","kind":"event","title":"UpstageAI/solarbox-opentelemetry-collector-contrib","date":"2025-04-22T02:21:32+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/solarbox-opentelemetry-collector-contrib","signal_url":"https://onlylabs.fyi/signals/6711e504-9365-4184-918b-c04c17b60b66","signal_json_url":"https://onlylabs.fyi/signals/6711e504-9365-4184-918b-c04c17b60b66/signal.json","text":"repo_forked · UpstageAI/solarbox-opentelemetry-collector-contrib · signal_desk=forks · occurred_at=2025-04-22T02:21:32+00:00 · url=https://github.com/UpstageAI/solarbox-opentelemetry-collector-contrib · raw={\"repo\":\"UpstageAI/solarbox-opentelemetry-collector-contrib\",\"parent\":\"open-telemetry/opentelemetry-collector-contrib\"}"},{"ref":"E60","kind":"event","title":"UpstageAI/tensorizer","date":"2025-01-17T07:12:34+00:00","date_source":"source","source_url":"https://github.com/UpstageAI/tensorizer","signal_url":"https://onlylabs.fyi/signals/8bc579b2-237e-454c-93f9-75fa94659122","signal_json_url":"https://onlylabs.fyi/signals/8bc579b2-237e-454c-93f9-75fa94659122/signal.json","text":"repo_forked · UpstageAI/tensorizer · signal_desk=forks · occurred_at=2025-01-17T07:12:34+00:00 · url=https://github.com/UpstageAI/tensorizer · raw={\"repo\":\"UpstageAI/tensorizer\",\"parent\":\"coreweave/tensorizer\"}"}]}