{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"Arcee AI 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/arcee","json_url":"https://onlylabs.fyi/analysis/arcee/evidence.json","generated_at":"2026-06-11T18:05:40.383Z","org":{"slug":"arcee","name":"Arcee AI","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/arcee"},"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":112,"web":0,"evidence":88,"signal_desks":{"hiring":2,"forks":12,"releases":28,"talking":0,"repos":18},"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":"arcee-ai/trinity-large-tech-report repository metadata","date":"2026-06-11T02:53:16.483891+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/trinity-large-tech-report","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/trinity-large-tech-report\n\nStars: 124\n\nForks: 5\n\nOpen issues: 0\n\nCreated: 2026-01-27T20:08:46Z\n\nPushed: 2026-02-19T02:01:44Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Arcee Trinity Large - Technical Report\n\n\"trinity\"\n

\n\nWe present the technical report for Arcee Trinity Large, a sparse Mixture-of-Experts model with 400B total parameters and 13B activated per token. Additionally, we report on Trinity Nano and Trinity Mini, with Trinity Nano having 6B total parameters with 1B activated per token, Trinity Mini having 26B total parameters with 3B activated per token. The models’ modern architecture includes interleaved local and global attention, gated attention, depth-scaled sandwich norm, and sigmoid routing for Mixture-of-Experts. For Trinity Large, we also introduce a new MoE load balancing strategy titled Soft-clamped Momentum Expert Bias Updates (SMEBU). We train the models using the Muon optimizer. All three models completed training with zero loss spikes. Trinity Nano and Trinity Mini were pre-trained on 10 trillion tokens, and Trinity Large was pre-trained on 17 trillion tokens. The model checkpoints are available on [Hugging Face](https://huggingface.co/arcee-ai)."},{"ref":"P2","kind":"page","title":"arcee-ai/Stable-Diffusion-text-to-image repository metadata","date":"2026-06-11T03:17:57.726266+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/Stable-Diffusion-text-to-image","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/Stable-Diffusion-text-to-image\n\nDescription: A simple stable diffusion text-to-image notebook\n\nStars: 3\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2023-03-03T15:09:57Z\n\nPushed: 2023-03-03T15:09:58Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Stable-Diffusion-text-to-image\nA simple stable diffusion text-to-image notebook"},{"ref":"P3","kind":"page","title":"arcee-ai/arcee-python repository metadata","date":"2026-06-11T03:17:57.424663+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/arcee-python","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/arcee-python\n\nDescription: The Arcee client for executing domain-adpated language model routines https://pypi.org/project/arcee-py/\n\nLanguage: Python\n\nStars: 28\n\nForks: 3\n\nOpen issues: 9\n\nCreated: 2023-06-08T21:52:18Z\n\nPushed: 2024-10-08T17:24:18Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Arcee Python Client\n\n> The Arcee Python client allows you to manage CPT, SFT, DPO, and Merge models on the Arcee Platform.\n\nThis client may be used as a CLI by invoking `arcee` from the terminal, or as an SDK for programmatic use by `import arcee` in Python.\n\nLearn more at https://docs.arcee.ai\n\n## Installation\n\n```\npip install --upgrade arcee-py\n```\n\n## Authenticating\n\nYour Arcee API key is obtained at https://app.arcee.ai\n\nIn bash:\n\n```\nexport ARCEE_API_KEY=********\n```\n\nIn notebook:\n\n```\nimport os\nos.environ[\"ARCEE_API_KEY\"] = \"********\"\n```\n\n(Optional) To customize the URL of the Arcee platform:\n\n```\nexport ARCEE_API_URL=\"https://your-url.arcee.ai\"\n```\n\n(Optional) To specify an organization to issue requests for:\n\n```\nexport ARCEE_ORG=\"my-organization\"\n```\n\nIf you do not specify an organization, your default organization will be used. You can change the default in your Arcee account settings.\n\n## Upload Context\n\nUpload context for retriever training:\n\n```\nimport arcee\narcee.upload_docs(\"pubmed\", docs=[{\"doc_name\": \"doc1\", \"doc_text\": \"foo\"}, {\"doc_name\": \"doc2\", \"doc_text\": \"bar\"}])\n```\n\n## Upload Finetuning Dataset\n\n### Method 1: Via CSV\n\n```\narcee.upload_instructions_from_csv(\n\"finetuning-dataset-name\",\ncsv_path=\"./your_data.csv\",\nprompt_column=\"prompt\",\ncompletion_column=\"completion\"\n)\n```\n\n### Method 2: Via HF Dataset\n\nNOTE: you will need to set `HUGGINGFACE_TOKEN` in your environment to use this function.\n\n```\narcee.api.upload_hugging_face_dataset_qa_pairs(\n\"my_qa_pairs\",\nhf_dataset_id=\"org/dataset\",\ndataset_split=\"train\",\ndata_format=\"chatml\"\n)\n```\n\n## Using the Arcee CLI\n\nYou can easily train and use your Domain-Adapted Language Model (DALM) with Arcee using the CLI. Follow these steps post installation to train and utilize your DALM:\n\n### Upload Context\n\nUpload a context file for your DALM like,\n```shell\narcee upload context pubmed --file d"},{"ref":"P4","kind":"page","title":"arcee-ai/DALM repository metadata","date":"2026-06-11T03:17:57.309999+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DALM","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/DALM\n\nDescription: Domain Adapted Language Modeling Toolkit - E2E RAG\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 341\n\nForks: 47\n\nOpen issues: 12\n\nCreated: 2023-07-31T23:23:58Z\n\nPushed: 2024-11-08T01:43:12Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Domain Adapted Language Modeling Toolkit\n\n## Manifesto\n\nA great rift has emerged between general LLMs and the vector stores that are providing them with contextual information. The unification of these systems is an important step in grounding AI systems in efficient, factual domains, where they are utilized not only for their generality, but for their specificity and uniqueness. To this end, we are excited to open source the Arcee Domain Adapted Language Model (DALM) toolkit for developers to build on top of our Arcee open source Domain Pretrained (DPT) LLMs. We believe that our efforts will help as we begin next phase of language modeling, where organizations deeply tailor AI to operate according to their unique intellectual property and worldview. \n\n## Demo DALMs\n\nQuery example DALMs created by the Arcee Team.\n\n[DALM-Patent](https://app.arcee.ai) | [DALM-PubMed](https://app.arcee.ai) | [DALM-SEC](https://app.arcee.ai) | [DALM-Yours](https://app.arcee.ai) \n:-------------------------:|:-------------------------:|:-------------------------:|:-------------------------:\n[![](https://i.imgur.com/Geh28Q8.jpg)](https://app.arcee.ai) | [![](https://i.imgur.com/IY73TcV.jpg)](https://app.arcee.ai) | [![](https://i.imgur.com/XgWn1VI.jpg)](https://app.arcee.ai) | [![](https://i.imgur.com/7KOgcEX.png)](https://app.arcee.ai)\n\n## Research Contents\n\nThis repository primarily contains code for fine-tuning a **fully differential** Retrieval Augmented Generation (RAG-end2end) architecture. \n\n![E2E](https://i.imgur.com/SDoY0oq.png)\n\nFor the first time in the literature, we modified the initial RAG-end2end model ([TACL paper](https://aclanthology.org/2023.tacl-1.1/), [HuggingFace implementation](https://github.com/huggingface/transformers/tree/main/examples/research_projects/rag-end2end-retriever)) to work with decoder-only language models like Llama, Falcon, or GPT. We also incorporated the **in-batch negat"},{"ref":"P5","kind":"page","title":"arcee-ai/mergekit repository metadata","date":"2026-06-11T03:17:56.93267+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/mergekit","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/mergekit\n\nDescription: Tools for merging pretrained large language models.\n\nLanguage: Python\n\nLicense: LGPL-3.0\n\nStars: 7132\n\nForks: 729\n\nOpen issues: 267\n\nCreated: 2023-08-21T03:50:04Z\n\nPushed: 2026-05-06T05:15:16Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# mergekit\n\n[![License: LGPL v3](https://img.shields.io/badge/License-LGPL_v3-blue.svg)](https://www.gnu.org/licenses/lgpl-3.0)\n[![GitHub Actions Workflow Status](https://img.shields.io/github/actions/workflow/status/arcee-ai/mergekit/pre-commit.yml?label=Tests)](https://github.com/arcee-ai/mergekit/actions/workflows/pre-commit.yml)\n[![Arcee Discord](https://img.shields.io/badge/Arcee%20Discord-Arcee%20Discord?logo=discord&logoColor=white&color=5865F2)](https://discord.gg/arceeai)\n\n`mergekit` is a toolkit for merging pre-trained language models. `mergekit` uses an out-of-core approach to perform unreasonably elaborate merges in resource-constrained situations. Merges can be run entirely on CPU or accelerated with as little as 8 GB of VRAM. Many merging algorithms are supported, with more coming as they catch my attention.\n\n## Contents\n\n- [Why Merge Models?](#why-merge-models)\n- [Features](#features)\n- [Installation](#installation)\n- [Community & Support](#community--support)\n- [Contributing](#contributing)\n- [Community Tools](#community-tools)\n- [Usage](#usage)\n- [Merge Configuration](#merge-configuration)\n- [Parameter Specification](#parameter-specification)\n- [Tokenizer Configuration](#tokenizer-configuration)\n- [Chat Template Configuration](#chat-template-configuration)\n- [Examples](#examples)\n- [Merge Methods](#merge-methods)\n- [LoRA Extraction](#lora-extraction)\n- [Mixture of Experts Merging](#mixture-of-experts-merging)\n- [Evolutionary Merge Methods](#evolutionary-merge-methods)\n- [Multi-Stage Merging (`mergekit-multi`)](#multi-stage-merging-mergekit-multi)\n- [Raw PyTorch Model Merging (`mergekit-pytorch`)](#raw-pytorch-model-merging-mergekit-pytorch)\n- [Tokenizer Transplantation (`mergekit-tokensurgeon`)](#tokenizer-transplantation-mergekit-tokensurgeon)\n- [Citation](#citation)\n\n## Why Merge Models?\n\nModel merging is a powerful technique that allows combining the strengths of di"},{"ref":"P6","kind":"page","title":"arcee-ai/code-llama-rag repository metadata","date":"2026-06-11T03:17:56.782168+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/code-llama-rag","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/code-llama-rag\n\nDescription: The first RAG retriever tuned particularly for code and code Llama\n\nLanguage: Python\n\nStars: 12\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2023-09-28T14:44:56Z\n\nPushed: 2023-10-03T02:00:03Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n## Contents\n\n`scripts` directory has two scripts\n\n1. `python_funcs_info_dump.py` looks at the python modules available to the runtime and makes a csv of each modules's functions (certain filters are applied)\n2. `generate_qa.py` uses the csv generated from the above (made available via a commandline arg) and generates the required q&a file with four columns"},{"ref":"P7","kind":"page","title":"arcee-ai/notebooks repository metadata","date":"2026-06-11T03:17:56.711728+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/notebooks","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/notebooks\n\nDescription: Demo Notebooks showcasing Arcee and DALM\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 4\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2023-10-04T19:37:31Z\n\nPushed: 2023-10-04T19:59:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# notebooks\nDemo Notebooks showcasing Arcee and DALM\n\n* Train DALM end-to-end [[colab](https://colab.research.google.com/github/arcee-ai/notebooks/blob/main/Train_E2ERAG_Domain_Adapted_Language_Model.ipynb) | [file](https://github.com/arcee-ai/notebooks/blob/main/Train_E2ERAG_Domain_Adapted_Language_Model.ipynb)]"},{"ref":"P8","kind":"page","title":"arcee-ai/documentation repository metadata","date":"2026-06-11T03:17:56.527323+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/documentation","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/documentation\n\nDescription: Arcee docs repository\n\nStars: 0\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2023-11-02T12:49:11Z\n\nPushed: 2025-04-27T17:10:13Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Arcee DALMs Client Documentation\n\nWelcome to the Arcee client documentation! This guide will help you execute domain-adapted language model (DALM) routines using the Arcee client libraries.\n\n## Arcee DALMs\n\n### Installation\n\nTo install the Arcee package, simply run the following pip command:\n\n```bash\npip install arcee-py\n```\n\n### Authenticating\n\nObtain your Arcee API key from [app.arcee.ai](https://app.arcee.ai).\n\nIn bash:\n\n```bash\nexport ARCEE_API_KEY=your_api_key\n```\n\nIn a notebook:\n\n```python\nimport os\nos.environ[\"ARCEE_API_KEY\"] = \"your_api_key\"\n```\n\n### Upload Context\n\nUpload context for your domain-adapted language model to draw from.\n\n```python\nimport arcee\narcee.upload_doc(\"pubmed\", doc_name=\"doc1\", doc_text=\"whoa\")\n# Alternatively, you can upload multiple documents at once:\n# arcee.upload_docs(\"pubmed\", docs=[{\"doc_name\": \"doc1\", \"doc_text\": \"foo\"}, {\"doc_name\": \"doc2\", \"doc_text\": \"bar\"}])\n```\n\n### Train DALM\n\nTrain a DALM with the context you have uploaded.\n\n```python\nimport arcee\ndalm = arcee.train_dalm(\"medical_dalm\", context=\"pubmed\")\n# Wait for training to complete\narcee.get_dalm_status(\"medical_dalm\")\n```\n\nThe DALM training procedure refines your model in context and establishes an index for your model to utilize.\n\n### DALM Generation\n\nGenerate responses from your DALM:\n\n```python\nimport arcee\nmed_dalm = arcee.get_dalm(\"medical_dalm\")\nmed_dalm.generate(\"What are the components of Scoplamine?\")\n```\n\n### DALM Retrieval\n\nRetrieve documents relevant to a specific query, which can then be viewed directly or used with another LLM.\n\n```python\nimport arcee\nmed_dalm = arcee.get_dalm(\"medical_dalm\")\nmed_dalm.retrieve(\"my query\")\n```\n\n## Using the Arcee CLI\n\nThe Arcee CLI simplifies training and using your Domain-Adapted Language Model (DALM).\n\n### Upload Context\n\nUpload a context file for your DALM:\n\n```bash\narcee upload context pubmed --file doc1\n```\n\nUpload all files within a directory:\n\n```bash\narcee upload context pubmed --directory docs\n```"},{"ref":"P9","kind":"page","title":"arcee-ai/arcee-trainium-recipes repository metadata","date":"2026-06-11T03:17:56.447792+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/arcee-trainium-recipes","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/arcee-trainium-recipes\n\nDescription: The repository contains all the set-up required to execute trainium training jobs. \n\nLanguage: Python\n\nStars: 4\n\nForks: 1\n\nOpen issues: 1\n\nCreated: 2024-02-01T18:11:31Z\n\nPushed: 2025-02-11T15:46:00Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# arcee-trainium-recipes\nThe repository contains all the set-up required to execute trainium training jobs. \n\n## Data Preprocessing\nFor setting up Trainium CPT, it's crucial to have a tokenized and properly packed Hugging Face dataset that can be directly loaded from disk. In our experimental setup, we followed these steps:\n1. **Text Extraction and Tokenization**:\n- Initially, we extracted the entire text from papers and tokenized them in a distributed setting.\n\n2. **Packing Tokenized Data**:\n- We then packed the tokenized data in a format where each example contains 4096 tokens.\n- It's important to note that during the tokenization process, if the tokenized text exceeds 4096 tokens, it will be split into multiple tokens. Conversely, if it's fewer than 4096 tokens, it will be appended with other shorter examples.\n\n3. **Saving the Dataset**:\n- Finally, we saved the dataset to disk using the Hugging Face dataset's library function `save_to_disk`.\n\nThese preprocessing steps ensure that the data is formatted correctly for use with Trainium CPT. For further details on the preprocessing pipeline, refer to the documentation or code provided.\n\n## Model Training\n\nFirst, convert a Hugging Face pretrained checkpoint to the NxD sharded format, and then, begin training with the pretrained weights. This example uses `meta-llama/Llama-2-7b-hf`. It is recommended running this code from `/fsx/` on your ParallelCluster. Example: we used /fsx/llama2 as our working directory.\n\nTo run this code:\n\n* Clone the repository to `/fsx/llama2`.\n\n* Update the `DATA_PATH` in `tp_zero1_llama2_7b_hf_pretrain.sh` to point to your tokenized dataset (tokenized and packed data resulted from the data preprocessing part).\n\n* Make sure you have the `aws_neuron_venv_pytorch` virtualenv activated and install the dependecies by running the following commands:\n\n```\npython -m pip install neuronx_distributed --"},{"ref":"P10","kind":"page","title":"arcee-ai/Model-Tools repository metadata","date":"2026-06-11T03:17:56.155442+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/Model-Tools","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/Model-Tools\n\nLanguage: Python\n\nStars: 6\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2024-03-27T22:58:51Z\n\nPushed: 2024-05-06T18:23:04Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Model-Tools\n\nThis repository is an assorted toolkit of python scripts and systems designed for model diagnostics, test & validation, as well as overall convenience tools that focus on streamlining common operations.\n\n---\n\n## Table of Contents:\n- [EasyPEFTGUIPro](#easypeftguipro)\n- [Model Evaluation GUI](#model-evaluation-gui)\n- [More Tools...](#more-tools)\n\n---\n\n### EasyPEFTGUIPro\n\n`EasyPeftGUIPro` [aka easypeftguipro.py] is designed to simplify the process of fusing a language model with a compatible LoRA, then saving the resulting model to a user's directory of choice.\n\n#### Prerequisites\n\n- Python 3.6 or newer\n- `transformers` library\n- `torch` library\n- `tkinter` library\n\n#### Usage\n\n1. Clone this repository\n2. Navigate to the repository folder\n3. Run the `easypeftguipro.py` script\n4. Follow the on-screen prompts to select the base model, the desired LoRA, and an output directory to save the result.\n\n#### Considerations\n\nThis script relies on the `tkinter` library for interactive menus. An OS with a GUI interface is required.\nLoRAs made for a different model architecture or B number of parameters than the base language model selected will not successfully merge.\nLoRAs can however be merged with any pretrained model based on the same architecture and B of parameter size.\n\n---\n\n### Model Evaluation GUI\n\n

\nTo use Evaluation GUI, aka evalgui.py, simply run the script in a Python environment [if Windows]
\nor [if Linux] from the OS interface GUI through a CLI window and follow the steps below:\n

\n\n\n\n\n\n\n\n\n\n\n\n\n
1. Run Script, Select Model Folder2. Select Eval Sets
[!WARNING]\n> The `--reload` flag should not be used in production. It is only intended for development purposes.\n\n### Running with Multiple Workers (Parallel Processing)\n\nFor improved performance and parallel processing capabilities, you can specify either the absolute number of worker processes or the fraction of CPU cores to use. This is particularly useful for handling multiple requests simultaneously.\n\nYou can also set the `FASTMLX_NUM_WORKERS` environment variable to "},{"ref":"P12","kind":"page","title":"arcee-ai/BlockPruner repository metadata","date":"2026-06-11T03:17:55.692443+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/BlockPruner","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/BlockPruner\n\nDescription: A block pruning framework for LLMs.\n\nStars: 2\n\nForks: 3\n\nOpen issues: 0\n\nCreated: 2024-07-24T17:58:51Z\n\nPushed: 2024-06-20T05:43:28Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n

\n

\n\n
\n\nBlockPruner: Fine-grained Pruning for Large Language Models\n-----------------------------\n\n_**Longguang Zhong, Fanqi Wan, Ruijun Chen, Xiaojun Quan, Liangzhi Li**_\n
\n\n## Contents\n\n- [Overview](#overview)\n- [Evaluation Results](#evaluation_results)\n- [Quick Start](#quick-start)\n- [Evaluation](#evaluation)\n- [Citation](#citation)\n\n## Overview\nIn this work, we explored the phenomenon of block redundancy in existing LLMs and proposed a general block pruning framework. It first decomposes each Transformer layer into two minimal residual blocks (MHA or MLP). Then, we use our proposed block importance evaluation metric to assess the importance of each block. Finally, we iteratively prune the block with the lowest importance.\n

\n
\n

\n\n## Evaluation Results\nwe experiment with three series of models: [Llama2](https://huggingface.co/collections/meta-llama/llama-2-family-661da1f90a9d678b6f55773b), [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base), and [Qwen1.5](https://huggingface.co/collections/Qwen/qwen15-65c0a2f577b1ecb76d786524). We employ 7B and 13B models for Llama2 and Baichuan2, respectively, and 7B and 14B models for Qwen1.5. \n\nHere are the evaluation results.\n

\n
\n

\n\n## Quick Start\n### Setup\nTo use and evaluate BlockPruner, we have to install the following libraries first:\n```shell\ntorch==2.2.1\nlm_eval==0.4.0 # provided in ./lm_eval\n```\n\n### Usage\nBelow is the script for obtaining the pruning sequence of the corresponding model:\n```shell\nexport CUDA_VISIBLE_DEVICES=0\n\nmodel_name=Llama-2-7b\nnsamples=64\ndataset=alpaca\nblock_num=20\n\npython block_search.py \\\n--model-path models/${model_name}\\\n--block-type mix \\\n--cal-nsamples ${nsamples} \\\n--del-block-num ${block_num} \\\n--cal-dataset ${dataset} \\\n--ppl"},{"ref":"P13","kind":"page","title":"arcee-ai/PruneMe repository metadata","date":"2026-06-11T03:17:55.671121+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/PruneMe","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/PruneMe\n\nDescription: Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models\n\nLanguage: Python\n\nStars: 267\n\nForks: 32\n\nOpen issues: 1\n\nCreated: 2024-04-10T22:34:25Z\n\nPushed: 2024-04-23T00:03:24Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Layer Pruning of Large Language Models\n\nThis repository hosts the [unofficial] implementation of a layer pruning strategy for Large Language Models (LLMs) based on the insights from the paper \"[The Unreasonable Ineffectiveness of the Deeper Layers](https://arxiv.org/abs/2403.17887)\" by Andrey Gromov et al. The paper empirically demonstrates that LLMs can have a substantial number of their layers removed with minimal performance degradation, especially on question-answering benchmarks.\n\n## Summary of the Paper\n\nThe authors present a straightforward method for pruning layers from popular pretrained LLMs. They identify optimal blocks of layers for pruning by analyzing similarity across layers. The approach suggests that deeper layers in these LLMs are often more redundant than previously thought. After pruning, the model can be \"healed\" using Parameter-Efficient Fine-tuning (PEFT) methods like QLoRA to recover from the pruning-induced performance loss. These findings open avenues for significant computational resource reduction during both fine-tuning and inference stages, potentially improving memory and latency without severe impacts on performance.\n\n## Repository Structure\n\nThe codebase is divided into two main parts:\n\n### First compute the block/layer similarity given a dataset\n\nNavigate to the `compute_block_similarity` directory to run the layer similarity computation script.\n\n1. Open `run_layer_similarity.sh`.\n2. Replace the placeholder arguments with your model and dataset information:\n\n```bash\npython layer_similarity.py --model_path \"mistralai/Mistral-7B-Instruct-v0.2\" \\\n--dataset \"arcee-ai/sec-data-mini\" \\\n--dataset_column \"text\" \\\n--batch_size 8 \\\n--max_length 1024 \\\n--layers_to_skip 8 \\\n--dataset_size 4000 \\\n--dataset_subset \"train\" \n```\n\n3. Execute the script to get the most optimum layer/block range to prune.\n\n### Create the new model with the [Mergekit](https:"},{"ref":"P14","kind":"page","title":"arcee-ai/DistillKit repository metadata","date":"2026-06-11T03:17:55.557607+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DistillKit","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/DistillKit\n\nDescription: An Open Source Toolkit For LLM Distillation\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 959\n\nForks: 126\n\nOpen issues: 4\n\nCreated: 2024-07-31T22:16:09Z\n\nPushed: 2026-05-12T20:10:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# DistillKit\n\nA flexible and production-ready toolkit for knowledge distillation of large language models, supporting both online and offline distillation workflows with advanced logit compression.\n\nDistillKit powers the training of many of Arcee's popular open-source models, including [Virtuoso](https://huggingface.co/arcee-ai/Virtuoso-Large), [SuperNova Medius](https://huggingface.co/arcee-ai/SuperNova-Medius), and [Blitz](https://huggingface.co/arcee-ai/Arcee-Blitz).\n\n## Features\n\n- **Online Distillation**: Real-time teacher inference during student training\n- **Offline Distillation**: Train from pre-captured teacher outputs with advanced compression\n- **Advanced Logit Compression**: Novel polynomial approximation + quantization + bit-packing achieving vigorous compression ratios while preserving distillation quality\n- **Flexible Loss Functions**: Composable losses including KL divergence, JSD, TVD, ranking losses, and hidden state alignment\n- **Sparse & Dense Support**: Efficient sparse distributions (top-k) or exact dense distributions\n- **Battle-tested**: The infrastructure powering Arcee's distilled model releases\n- **HuggingFace Integration**: Built on Transformers, TRL, and Accelerate\n\n## Why DistillKit?\n\nWhile online distillation is straightforward, **offline distillation at scale** requires careful engineering. Simply storing top-k token-logit pairs becomes prohibitively expensive when distilling on billions of tokens.\n\nDistillKit's compression system is the result of months of experimentation to strike the delicate balance between storage costs, memory throughput, and distillation quality. Our approach:\n\n1. **Polynomial approximation** of the logit distribution curve\n2. **Error-diffusion quantization** of residuals to preserve quality\n3. **Bit-level packing** with arbitrary bit widths (1-64 bits)\n\nThis enables practical offline distillation workflows that would otherwise be infeas"},{"ref":"P15","kind":"page","title":"arcee-ai/EvolKit repository metadata","date":"2026-06-11T03:17:55.287038+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/EvolKit","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/EvolKit\n\nDescription: EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Models (LLMs). \n\nLanguage: Jupyter Notebook\n\nLicense: MIT\n\nStars: 257\n\nForks: 26\n\nOpen issues: 2\n\nCreated: 2024-08-07T11:04:05Z\n\nPushed: 2024-10-30T17:39:25Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# EvolKit\n\nEvolKit is an framework for automatically enhancing the complexity of instructions used in fine-tuning Large Language Models (LLMs). Our project aims to revolutionize the evolution process by leveraging open-source LLMs, moving away from closed-source alternatives.\n\n## Key Features\n\n- Automatic instruction complexity enhancement\n- Integration with open-source LLMs\n- Streamlined fine-tuning process\n- Support for various datasets from Hugging Face\n- Flexible configuration options for optimization\n\n## Installation\n\nTo set up EvolKit, follow these steps:\n\n1. Clone the repository:\n\n```\ngit clone https://github.com/arcee-ai/EvolKit.git\ncd EvolKit\n```\n\n2. Install the required dependencies:\n\n```\npip install -r requirements.txt\n```\n\n## Usage\n\nTo run the AutoEvol script, use the following command structure:\n\n```\npython run_evol.py --dataset [options]\n```\n\n### Required Parameters:\n\n- `--dataset `: The name of the dataset on Hugging Face to use.\n- `--model `: Model to use for evolving instructions.\n- `--generator `: Type of generator to use ('openrouter' or 'vllm').\n- `--batch_size `: Number of instructions to process in each batch.\n- `--num_methods `: Number of evolution methods to use.\n- `--max_concurrent_batches `: Maximum number of batches to process concurrently (in our experiment, a cluster of 8xH100 hosting Qwen2-72B-Instruct-GPTQ-Int8 can handle batch size of 50 concurrently).\n- `--evolve_epoch `: Maximum number of epochs for evolving each instruction.\n- `--output_file `: Name of the output file to save results.\n\n### Optional Parameters:\n\n- `--dev_set_size `: Number of samples to use in the development set. Use -1 for no devset. Default is -1. (We do not recommend using a dev set since it w"},{"ref":"P16","kind":"page","title":"arcee-ai/DAM repository metadata","date":"2026-06-11T03:17:55.01221+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DAM","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/DAM\n\nLanguage: Python\n\nStars: 56\n\nForks: 7\n\nOpen issues: 3\n\nCreated: 2024-08-13T03:42:28Z\n\nPushed: 2024-11-06T17:48:40Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Differentiable Adaptive Merging (DAM)\n\n\"Project\n\nDifferentiable Adaptive Merging (DAM) automates the merging of multiple LLMs with unique capabilities, optimizing the balance between models for improved data efficiency and reduced computational costs. DAM outperforms traditional and evolutionary methods, offering a scalable solution for versatile AI systems. Extensive experiments validate DAM's superiority across various model merging scenarios.\n\n## Steps to Run the Workflow\n\nThis repository contains the implementation for running the merging coefficient tuning process.\n\n### 1. Create the Merged Model\nFirst, create the merged model by running the `merge.py` script found in the `dam` folder. The resulting merged model will contain untrained coefficients.\n\nIn this step, we assign a trainable coefficient for each column of each model's layer norms, embedding layers, and linear layers as specified by the user. These coefficients will be optimized during the training process to achieve the best integration of the models.\n\n#### Command:\n\n```bash\npython dam/merge.py mistralai/Mistral-7B-v0.1 augmxnt/shisa-gamma-7b-v1 WizardLM/WizardMath-7B-V1.1 arcee-train/Abel-7B-002-truncated-embeds --device cuda --output_path ./merged_model --repo_id arcee-train/[prefix]-untrained-merge\n```\n\n#### Arguments:\n- `base_model_id`: ID of the base model. All layers of this model will be replaced with DAM layers.\n- `model_ids`: IDs of the models to merge. The linear layers from these models will be used.\n- `--output_path`: Path where the merged model will be saved.\n- `--device`: Device to use for computation (e.g., 'cpu', 'cuda').\n- `--repo_id`: Repository ID where the merged model will be pushed.\n- `--use_base_model`: If specified, trainable coefficients will also be added to the base model's linear layers. This is optional.\n\n### 2. Prepare the Dataset\n\nTo prepare the dataset, navigate to the `dam/data` folder and run `create_merge_dataset.py`. This"},{"ref":"P17","kind":"page","title":"arcee-ai/aws-samples repository metadata","date":"2026-06-11T03:17:54.835154+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/aws-samples","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/aws-samples\n\nDescription: Developer resources to work with Arcee models on AWS\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 8\n\nForks: 2\n\nOpen issues: 0\n\nCreated: 2024-09-03T13:42:00Z\n\nPushed: 2025-10-03T14:30:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\nThis repository contains developer resources demonstrating how to deploy and use various Arcee models on Amazon SageMaker.\n\nYou're welcome to use them in your projects. Of course, we will always appreciate proper credit and a friendly message :)\n\nFor information or to discuss how Arcee can help your business, please contact julien@arcee.ai.\n\n## Models\n\nThe following Arcee models are featured in the sample notebooks:\n\n1. [Llama-Spark](https://huggingface.co/arcee-ai/Llama-Spark): A powerful 8B parameter model built on the foundation of Llama-3.1-8B, excelling in reasoning, creative writing, and coding tasks.\n\n2. [Arcee-Scribe](https://huggingface.co/arcee-ai/Arcee-Scribe): A versatile 7B parameter chat model with strong reasoning abilities, particularly adept at creative writing tasks.\n\n3. [Arcee-Nova](https://huggingface.co/arcee-ai/Arcee-Nova): A large language model with performance approaching that of GPT-4 (as of May 2023), built on Qwen2-72B-Instruct.\n\n4. [Arcee-Spark](https://huggingface.co/arcee-ai/Arcee-Spark): A powerful 7B parameter model that outperforms many larger models, offering a 32K context size.\n\n5. [Arcee-Lite](https://huggingface.co/arcee-ai/arcee-lite): A compact yet powerful 1.5B parameter model, ideal for embedded systems and resource-constrained environments.\n\n6. [Arcee-Agent](https://huggingface.co/arcee-ai/Arcee-Agent): A 7B parameter model specifically designed for function calling and tool use, excelling at interpreting and executing function calls.\n\n7. Arcee-SuperNova: a 70B model outperforming Llama 70B-Instruct, as well Llama 405B, Claude Sonnet 3.5 and GPT-4o in many general benchmarks.\n\n8. [Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite): an 8B distilled version of the larger Llama-3.1-405B-Instruct model.\n\n9. [SuperNova-Medius](https://huggingface.co/arcee-ai/SuperNova-Medius): a 14B parameter language model"},{"ref":"P18","kind":"page","title":"arcee-ai/SuperNova-Evals repository metadata","date":"2026-06-11T03:17:54.828021+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/SuperNova-Evals","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/SuperNova-Evals\n\nLanguage: Shell\n\nStars: 0\n\nForks: 1\n\nOpen issues: 0\n\nCreated: 2024-09-10T15:18:45Z\n\nPushed: 2024-09-10T16:40:12Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Arcee Llama-3.1-SuperNova Evaluation Reports\n\nThis repository contains a collection of evaluation reports generated for **Arcee's Llama-3.1-SuperNova model** using **Hugging Face's** fork of the **lm-evaluation-harness** that appeared in our release blogpost."},{"ref":"P19","kind":"page","title":"arcee-ai/in-context-learning repository metadata","date":"2026-06-11T03:17:54.740378+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/in-context-learning","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/in-context-learning\n\nLanguage: Python\n\nStars: 3\n\nForks: 1\n\nOpen issues: 1\n\nCreated: 2024-11-25T17:27:10Z\n\nPushed: 2024-12-24T01:11:19Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n# LLM Context Enhancement Experiment\n\nThis project implements an experimental framework for evaluating how providing relevant high quality context affects the quality of language model responses. It uses a vector database to retrieve similar question-answer pairs and compares model outputs with and without this additional context.\n\n## Overview\n\nThe system:\n1. Loads reference QA pairs from specified datasets\n2. Stores them in a vector database for similarity search\n3. For each experimental question:\n- Retrieves similar QA pairs as context\n- Generates responses both with and without context\n- Evaluates response quality using a reward model\n- Stores results for analysis\n\n## Features\n\n- Parallel processing for efficient vector database population\n- Support for multiple LLM architectures\n- Configurable embedding and reward models\n- SQLite results storage with comprehensive metrics\n- GPU acceleration support\n- Batched processing for memory efficiency\n\n## Requirements\n\n- Python 3.8+\n- PyTorch\n- Transformers\n- vLLM\n- LangChain\n- ChromaDB\n- SQLAlchemy\n- Datasets (HuggingFace)\n- tqdm\n\n## Installation\n\n1. Clone the repository\n2. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## Configuration\n\nEdit `config.py` to customize:\n\n- Dataset sources\n- Model selections\n- Database paths\n- Experiment parameters\n\nDefault configuration:\n```python\nreference_datasets = [\n(\"mlabonne/orca-agentinstruct-1M-v1-cleaned\", \"default\"),\n]\nexperiment_dataset = \"HuggingFaceTB/smoltalk\"\nembedding_model = \"BAAI/bge-small-en-v1.5\"\nllm_model = \"Qwen/Qwen2.5-7B-Instruct\"\nreward_model = \"internlm/internlm2-7b-reward\"\n```\n\n## Usage\n\n### Quick Start\n\nRun the complete experiment:\n```bash\nbash run_experiment.sh\n```\n\nThis will:\n1. Populate the vector database using parallel processing\n2. Execute the main experiment\n3. Store results in SQLite database\n\n### Manual Execution\n\n1. Populate vector database:\n```bash\npython parallel_insertion.py --use_gpu\n```\n\n2. Run experiment:\n```bash\npython main"},{"ref":"P20","kind":"page","title":"arcee-ai/KidRails repository metadata","date":"2026-06-11T03:17:54.429735+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/KidRails","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/KidRails\n\nLanguage: Python\n\nStars: 16\n\nForks: 5\n\nOpen issues: 0\n\nCreated: 2025-02-11T16:28:50Z\n\nPushed: 2025-05-20T16:44:43Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# KidRails: Replicating a Child-Safe LLM Model\n\nThis repository provides the code, data references, and instructions necessary to replicate our KidRails model—an open-source, child-safe large language model (LLM) built on the KidRails framework. The project was developed to set a new industry standard for age-appropriate, transparent AI interactions for children, and to promote collaboration among educators, developers, and researchers.\n\n## Table of Contents\n- Overview\n- Project Motivation\n- Model & Training Process\n- License\n- Acknowledgments\n\n## Overview\n\nKidRails is an LLM adapted specifically for ensuring safe, age-appropriate interactions with children. By leveraging a model-agnostic, open-source approach, our framework builds upon robust safety mechanisms and transparent training processes. The repository includes:\n- Code for training and fine-tuning the LLM (based on Llama 3.1 8B) for child-safe responses.\n- Data processing scripts to handle our training dataset, which includes curated Golden QA pairs.\n- Utilities for evaluating model performance against defined safety and age-appropriateness metrics.\n\n## Project Motivation\n\nAs LLMs become increasingly integrated into digital experiences for children, ensuring their safety is paramount. Our key motivations were:\n- **Choosing Llama 3.1:** \nOur team conducted extensive testing across various models. Llama 3.1 was selected for its balance of performance and efficiency, complemented by Arcee AI’s expertise in developing smaller yet highly effective models.\n- **Open-Source Commitment:** \nMaking KidRails open-source was crucial to set a new benchmark in child-safe AI. By sharing all training data and methods, we empower developers and researchers worldwide to audit, contribute, and adapt the model for diverse applications.\n- **Robust Safety Measures:** \nThe model incorporates real Golden QA pairs to ensure responses are both safe and encouraging for children. Additionally, we employed a novel “spectrum” training process to "},{"ref":"P21","kind":"page","title":"arcee-ai/wipro-pump-demo repository metadata","date":"2026-06-11T03:17:54.157379+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/wipro-pump-demo","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/wipro-pump-demo\n\nLanguage: Python\n\nStars: 0\n\nForks: 0\n\nOpen issues: 0\n\nCreated: 2025-04-24T19:05:03Z\n\nPushed: 2025-04-24T19:05:16Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Mock System Status Pump API\n\nThis project provides a simple Flask-based API to simulate sensor data (vibration, temperature, pressure) for a mock pump (\"Rig 42\"). It's designed for use in demos, such as the PumpGuard 20 concept, allowing interaction without needing real hardware.\n\n## Features\n\n* Simulates normal operating conditions.\n* Simulates specific anomalies:\n* High vibration (> 3.0g)\n* Rapid temperature increase (> 0.5°C/min)\n* Provides REST endpoints to get status and control the simulation mode.\n* Uses `uv` for environment management and execution.\n\n## Setup and Running\n\n1. **Prerequisites:**\n* Python 3.x\n* `uv` (Install from [astral-sh/uv](https://github.com/astral-sh/uv))\n* A Unix-like shell (bash, zsh)\n\n2. **Make the script executable (first time only):**\n```bash\nchmod +x run.sh\n```\n\n3. **Run the server:**\n```bash\n./run.sh\n```\nThis script will:\n* Create a Python virtual environment (`.venv`) if it doesn't exist.\n* Install the required dependency (Flask) using `uv`.\n* Start the Flask server.\n\nThe server will run on `http://0.0.0.0:5001` by default, meaning it's accessible from your local machine and potentially other devices on the same network.\n\n## API Endpoints\n\nThe server runs on port `5001` by default. Replace `localhost` with the actual IP address if accessing from another machine on the network.\n\n### 1. Get Pump Status\n\nRetrieves the latest simulated sensor data.\n\n* **Endpoint:** `GET /status`\n* **Method:** `GET`\n* **`curl` Example:**\n```bash\ncurl http://localhost:5001/status\n```\n* **Example Response:**\n```json\n{\n\"pump_id\": \"Rig 42\",\n\"timestamp\": \"2025-04-24T16:49:00Z\",\n\"vibration\": 1.234,\n\"temperature\": 62.51,\n\"pressure\": 110.5\n}\n```\n\n### 2. Control Simulation Mode\n\nChanges the behavior of the data simulation.\n\n* **Endpoint:** `POST /control`\n* **Method:** `POST`\n* **Request Body:** JSON object with a `mode` key.\n* Valid modes: `\"normal\"`, `\"high_vibration\"`, `\"rapid_temp_increase\"`\n* **`curl` Examples:**\n\n* **Set to Normal:**\n```bash\ncurl -X POST -"},{"ref":"P22","kind":"page","title":"arcee-ai/anymcp repository metadata","date":"2026-06-11T03:17:54.0525+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/anymcp","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/anymcp\n\nLanguage: Python\n\nStars: 8\n\nForks: 3\n\nOpen issues: 0\n\nCreated: 2025-05-06T09:20:06Z\n\nPushed: 2025-06-03T07:34:12Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# AnyMCP\n\nAn adapter library for Model Context Protocol (MCP) SSE servers to connect as stdio.\n\n## Overview\n\nAnyMCP provides a bridge between SSE-based (Server-Sent Events) MCP servers and standard input/output (stdio). It allows you to connect to remote model servers that implement MCP over SSE and interact with them using traditional stdio interfaces.\n\n## Features\n\n- Connect to MCP servers via SSE endpoints\n- Bridge SSE communication to standard input/output\n- Maintain persistent connections with automatic reconnection\n- Support for authentication via bearer tokens\n- Comprehensive logging with adjustable verbosity\n- Configurable timeouts and heartbeat intervals\n\nThis package is meant to be used with Arcee [AnyMCP](https://mcp.arcee.ai).\nArcee AnyMCP makes it super easy to deploy your own MCP servers.\n\n## Installation\n\n### Using pip\n\n```bash\npip install anymcp\n```\n\n### From source\n\n```bash\ngit clone https://github.com/arcee-ai/anymcp.git\ncd anymcp\npip install -e .\n```\n\n## Usage\n\n### Command Line Interface\n\nConnect to an SSE-based MCP server:\n\n```bash\nanymcp connect http://localhost:8000/sse\n```\n\nWith authentication:\n\n```bash\nanymcp connect http://localhost:8000/sse --token YOUR_AUTH_TOKEN\n```\n\nAdd custom headers:\n\n```bash\nanymcp connect http://localhost:8000/sse --header \"X-Custom-Header=Value\"\n```\n\nEnable debug logging:\n\n```bash\nanymcp connect http://localhost:8000/sse --debug\n```\n\n### Python API\n\nUse AnyMCP in your Python applications:\n\n```python\nimport asyncio\nfrom anymcp import connect_sse_as_stdio\n\nasync def main():\nasync with connect_sse_as_stdio(\nsse_url=\"http://localhost:8000/sse\",\ntoken=\"YOUR_AUTH_TOKEN\",\ntimeout=5.0,\nsse_read_timeout=300.0\n) as (reader, writer):\n# Now your application can communicate with the MCP server\n# through reader and writer streams\npass\n\nif __name__ == \"__main__\":\nasyncio.run(main())\n```\n\n## Development\n\n### Setup\n\n```bash\n# Install in development mode\npip install -e \".[dev]\"\n```\n\n### Running Tests\n\n```bash\nmake test\n```\n\n### Code Quality\n\n```"},{"ref":"P23","kind":"page","title":"arcee-ai/NeMo-RL repository metadata","date":"2026-06-11T03:17:54.026827+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/NeMo-RL","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/NeMo-RL\n\nDescription: Scalable toolkit for efficient model reinforcement\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 12\n\nForks: 3\n\nOpen issues: 1\n\nCreated: 2025-08-14T00:08:13Z\n\nPushed: 2026-01-27T05:19:49Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# Arcee RLKit\n\n**⚠️ This is a fork of NeMo-RL maintained by Arcee AI for internal use, made public for ease of tracking upstream changes. While the fork's code remains under the same license as the upstream repository, we will not provide support. Here be dragons!**\n\nIf you're looking for the original pre-fork setup instructions, [click here](/docs/README_OLD.md)."},{"ref":"P24","kind":"page","title":"arcee-ai/pybubble repository metadata","date":"2026-06-11T03:17:53.597123+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/pybubble","signal_url":null,"signal_json_url":null,"text":"# arcee-ai/pybubble\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 80\n\nForks: 3\n\nOpen issues: 0\n\nCreated: 2025-11-16T04:37:22Z\n\nPushed: 2026-02-18T20:11:58Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n# pybubble\n\nA simple wrapper around [bubblewrap](https://github.com/containers/bubblewrap) to create sandboxed environments for executing code. It works without Docker or other daemon-based container runtimes, using shared read-only root filesystems for quick (1-2ms) setup times.\n\nWhile these environments are sandboxed and provide protection from accidental modification of your host system by overzealous LLMs, **pybubble is not sufficient to protect you against actively malicious code**. In general, while containerization solutions like pybubble or Docker offer a reasonable degree of protection from accidental damage, when accepting input from the public you should consider using virtualization in place of or in addition to containers.\n\nFeel free to submit bug reports and pull requests via GitHub, but note that Arcee is not committing to long-term support of this software. I wrote this library in my spare time to solve an irritating problem with building code execution environments, so expect a pace of updates consistent with \"time I have while waiting for a debug run to finish\".\n\nDue to relying on Linux kernel features to operate, pybubble is not compatible with macOS or Windows.\n\n## Setup\n\nInstall `bwrap`. On Ubuntu, do:\n\n```bash\n$ sudo apt-get install bubblewrap\n```\n\nOptionally, for overlay filesystem support (writable rootfs without modifying the original):\n\n```bash\n$ sudo apt-get install fuse-overlayfs\n```\n\nFor outbound internet access (or port forwarding via `enable_outbound=True`), install `slirp4netns`:\n\n```bash\n$ sudo apt-get install slirp4netns\n```\n\nBasic internal networking (`enable_network=True`) does not require `slirp4netns`.\n\nThen, add `pybubble` to your project.\n\n```bash\n$ uv add pybubble\n```\n\n## Root filesystem archives\n\nPrebuilt wheels for pybubble come bundled with an x86 Alpine Linux root filesystem archive based on `default-rootfs.dockerfile`. It comes with:\n\n- Python\n- uv\n- bash\n- ripgrep\n- cURL & wget\n- numpy\n- pandas\n- httpx & r"},{"ref":"P25","kind":"page","title":"arcee-ai/DALM 0.0.2","date":"2026-06-11T03:17:06.845377+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DALM/releases/tag/0.0.2","signal_url":null,"signal_json_url":null,"text":"# 0.0.2\n\nRepository: arcee-ai/DALM\n\nTag: 0.0.2\n\nPublished: 2023-09-20T21:06:27Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* docs and fix loading data in retriever only by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/44\n* Chore/training experiment by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/47\n\n**Full Changelog**: https://github.com/arcee-ai/DALM/compare/0.0.1...0.0.2"},{"ref":"P26","kind":"page","title":"arcee-ai/DALM 0.0.1","date":"2026-06-11T03:17:06.837743+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DALM/releases/tag/0.0.1","signal_url":null,"signal_json_url":null,"text":"# 0.0.1\n\nRepository: arcee-ai/DALM\n\nTag: 0.0.1\n\nPublished: 2023-09-20T01:18:12Z\n\nPrerelease: no\n\nRelease notes:\n# Open Source DALM 🚀 \n\n## What's Changed\n* Casual rag by @shamanez in https://github.com/arcee-ai/DALM/pull/1\n* rag e2e first commit by @shamanez in https://github.com/arcee-ai/DALM/pull/2\n* Remove hardcoded dataset by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/5\n* revisisted the LLM loss function by @shamanez in https://github.com/arcee-ai/DALM/pull/6\n* Add static methods for bnb and lora configs by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/7\n* added initial evals by @shamanez in https://github.com/arcee-ai/DALM/pull/8\n* Refactor rag e2e evaluation by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/9\n* [1] repo setup: tests, linting, ci, typing by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/10\n* [2] eval and datasets dirs setup by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/13\n* Refactor the codebase by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/14\n* Fix accelerator issue by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/16\n* added the peft layey attachment by @shamanez in https://github.com/arcee-ai/DALM/pull/18\n* Fix formatting issue by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/19\n* Add the question answer generation script by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/20\n* Distribute typing by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/24\n* Fix retriever only training by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/25\n* Take max length as CLI parameters by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/27\n* Updated the current README. by @shamanez in https://github.com/arcee-ai/DALM/pull/28\n* Add login to eval script. Fix minor problems by @SachiraKuruppu in https://github.com/arcee-ai/DALM/pull/29\n* revisited the README and max token lengths by @shamanez in https://github.com/arcee-ai/DALM/pull/30\n* Max token lengths args by @shamanez in https://github.com/arcee-ai/DALM/pull/31\n* Update eval_with_hnsw.py by @shamanez in https://github.com/arcee-ai/DALM/pull/35\n* License and Example DALMs by @Jacobsolawetz"},{"ref":"P27","kind":"page","title":"arcee-ai/DALM 0.0.3","date":"2026-06-11T03:17:06.694918+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DALM/releases/tag/0.0.3","signal_url":null,"signal_json_url":null,"text":"# 0.0.3\n\nRepository: arcee-ai/DALM\n\nTag: 0.0.3\n\nPublished: 2023-09-21T01:46:56Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* move exp into folder by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/48\n* Fix dataset load by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/49\n\n**Full Changelog**: https://github.com/arcee-ai/DALM/compare/0.0.2...0.0.3"},{"ref":"P28","kind":"page","title":"arcee-ai/DALM 0.0.4","date":"2026-06-11T03:17:06.617622+00:00","date_source":null,"source_url":"https://github.com/arcee-ai/DALM/releases/tag/0.0.4","signal_url":null,"signal_json_url":null,"text":"# 0.0.4\n\nRepository: arcee-ai/DALM\n\nTag: 0.0.4\n\nPublished: 2023-09-21T22:51:11Z\n\nPrerelease: no\n\nRelease notes:\n## What's Changed\n* align names to rage2e params by @Ben-Epstein in https://github.com/arcee-ai/DALM/pull/52\n\n**Full Changelog**: https://github.com/arcee-ai/DALM/compare/0.0.3...0.0.4"},{"ref":"E1","kind":"event","title":"arcee-ai/Trinity-Mini","date":"2025-12-01T16:12:10+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Mini","signal_url":"https://onlylabs.fyi/signals/5b0a8b46-a677-408c-aa20-018d31cecad2","signal_json_url":"https://onlylabs.fyi/signals/5b0a8b46-a677-408c-aa20-018d31cecad2/signal.json","text":"model_released · arcee-ai/Trinity-Mini · signal_desk=releases · occurred_at=2025-12-01T16:12:10+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Mini · hf_downloads=14853 · hf_likes=191 · hf_params=26123974400 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E2","kind":"event","title":"arcee-ai/Trinity-Large-Thinking","date":"2026-04-01T03:35:06+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking","signal_url":"https://onlylabs.fyi/signals/429af5af-ee30-4a25-874a-139c404e5dec","signal_json_url":"https://onlylabs.fyi/signals/429af5af-ee30-4a25-874a-139c404e5dec/signal.json","text":"model_released · arcee-ai/Trinity-Large-Thinking · signal_desk=releases · occurred_at=2026-04-01T03:35:06+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Large-Thinking · hf_downloads=10664 · hf_likes=182 · hf_params=398635286016 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E3","kind":"event","title":"arcee-ai/Trinity-Large-Preview","date":"2026-01-27T14:52:00+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Large-Preview","signal_url":"https://onlylabs.fyi/signals/b357f482-7717-4ab4-ae03-f146b4efef08","signal_json_url":"https://onlylabs.fyi/signals/b357f482-7717-4ab4-ae03-f146b4efef08/signal.json","text":"model_released · arcee-ai/Trinity-Large-Preview · signal_desk=releases · occurred_at=2026-01-27T14:52:00+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Large-Preview · hf_downloads=523 · hf_likes=180 · hf_params=398635286016 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E4","kind":"event","title":"arcee-ai/Homunculus","date":"2025-06-02T18:46:57+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Homunculus","signal_url":"https://onlylabs.fyi/signals/41f75527-4bba-4abe-85bb-afeaf74bf2bd","signal_json_url":"https://onlylabs.fyi/signals/41f75527-4bba-4abe-85bb-afeaf74bf2bd/signal.json","text":"model_released · arcee-ai/Homunculus · signal_desk=releases · occurred_at=2025-06-02T18:46:57+00:00 · url=https://huggingface.co/arcee-ai/Homunculus · hf_downloads=15 · hf_likes=99 · hf_params=12458808320 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E5","kind":"event","title":"arcee-ai/AFM-4.5B","date":"2025-07-29T15:04:18+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B","signal_url":"https://onlylabs.fyi/signals/cca31fed-0731-4479-8109-726c875f6af0","signal_json_url":"https://onlylabs.fyi/signals/cca31fed-0731-4479-8109-726c875f6af0/signal.json","text":"model_released · arcee-ai/AFM-4.5B · signal_desk=releases · occurred_at=2025-07-29T15:04:18+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B · hf_downloads=1619 · hf_likes=96 · hf_params=4619189760 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E6","kind":"event","title":"arcee-ai/Arcee-Blitz","date":"2025-02-07T07:55:43+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Arcee-Blitz","signal_url":"https://onlylabs.fyi/signals/5af8cd6f-d935-4816-9d1d-fbb1a85133dc","signal_json_url":"https://onlylabs.fyi/signals/5af8cd6f-d935-4816-9d1d-fbb1a85133dc/signal.json","text":"model_released · arcee-ai/Arcee-Blitz · signal_desk=releases · occurred_at=2025-02-07T07:55:43+00:00 · url=https://huggingface.co/arcee-ai/Arcee-Blitz · hf_downloads=17 · hf_likes=79 · hf_params=23572403200 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E7","kind":"event","title":"arcee-ai/Trinity-Nano-Preview","date":"2025-12-01T19:16:24+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Nano-Preview","signal_url":"https://onlylabs.fyi/signals/f8a9e0d5-b686-4259-84b2-13c5d5c1f48e","signal_json_url":"https://onlylabs.fyi/signals/f8a9e0d5-b686-4259-84b2-13c5d5c1f48e/signal.json","text":"model_released · arcee-ai/Trinity-Nano-Preview · signal_desk=releases · occurred_at=2025-12-01T19:16:24+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Nano-Preview · hf_downloads=25660 · hf_likes=77 · hf_params=6120003328 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E8","kind":"event","title":"arcee-ai/Trinity-Large-TrueBase","date":"2026-01-27T10:15:24+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Large-TrueBase","signal_url":"https://onlylabs.fyi/signals/a4e0c878-5f8b-40c6-9f98-4ee804203235","signal_json_url":"https://onlylabs.fyi/signals/a4e0c878-5f8b-40c6-9f98-4ee804203235/signal.json","text":"model_released · arcee-ai/Trinity-Large-TrueBase · signal_desk=releases · occurred_at=2026-01-27T10:15:24+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Large-TrueBase · hf_downloads=226 · hf_likes=67 · hf_params=398635286016 · pipeline=text-generation · license=other"},{"ref":"E9","kind":"event","title":"arcee-ai/Trinity-Large-Base","date":"2026-01-27T11:31:37+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Large-Base","signal_url":"https://onlylabs.fyi/signals/d077f164-5763-41f9-925d-f7baa485ef29","signal_json_url":"https://onlylabs.fyi/signals/d077f164-5763-41f9-925d-f7baa485ef29/signal.json","text":"model_released · arcee-ai/Trinity-Large-Base · signal_desk=releases · occurred_at=2026-01-27T11:31:37+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Large-Base · hf_downloads=263 · hf_likes=58 · hf_params=398635286016 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E10","kind":"event","title":"arcee-ai/Arcee-Maestro-7B-Preview","date":"2025-02-10T23:23:19+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Arcee-Maestro-7B-Preview","signal_url":"https://onlylabs.fyi/signals/b1f3057c-b69a-4bba-9782-91814d66b9bd","signal_json_url":"https://onlylabs.fyi/signals/b1f3057c-b69a-4bba-9782-91814d66b9bd/signal.json","text":"model_released · arcee-ai/Arcee-Maestro-7B-Preview · signal_desk=releases · occurred_at=2025-02-10T23:23:19+00:00 · url=https://huggingface.co/arcee-ai/Arcee-Maestro-7B-Preview · hf_downloads=55 · hf_likes=38 · hf_params=7612756480 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E11","kind":"event","title":"arcee-ai/GLM-4-32B-Base-32K","date":"2025-06-23T14:29:20+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/GLM-4-32B-Base-32K","signal_url":"https://onlylabs.fyi/signals/c525a4e1-e143-4008-83f5-8f63e0d71874","signal_json_url":"https://onlylabs.fyi/signals/c525a4e1-e143-4008-83f5-8f63e0d71874/signal.json","text":"model_released · arcee-ai/GLM-4-32B-Base-32K · signal_desk=releases · occurred_at=2025-06-23T14:29:20+00:00 · url=https://huggingface.co/arcee-ai/GLM-4-32B-Base-32K · hf_downloads=20 · hf_likes=38 · hf_params=32563513344 · pipeline=text-generation · license=mit · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E12","kind":"event","title":"arcee-ai/mergekit","date":"2023-08-21T03:50:04+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/mergekit","signal_url":"https://onlylabs.fyi/signals/1304d1b2-f092-4d48-9522-ea120a0dd170","signal_json_url":"https://onlylabs.fyi/signals/1304d1b2-f092-4d48-9522-ea120a0dd170/signal.json","text":"repo_new · arcee-ai/mergekit · signal_desk=repos · occurred_at=2023-08-21T03:50:04+00:00 · url=https://github.com/arcee-ai/mergekit · stars=7134 · raw={\"repo\":\"arcee-ai/mergekit\",\"description\":\"Tools for merging pretrained large language models.\",\"language\":\"Python\"}"},{"ref":"E13","kind":"event","title":"arcee-ai/AFM-4.5B-Base","date":"2025-07-29T15:01:10+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-Base","signal_url":"https://onlylabs.fyi/signals/2e6a8619-e906-45af-8cac-a777dee82a85","signal_json_url":"https://onlylabs.fyi/signals/2e6a8619-e906-45af-8cac-a777dee82a85/signal.json","text":"model_released · arcee-ai/AFM-4.5B-Base · signal_desk=releases · occurred_at=2025-07-29T15:01:10+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-Base · hf_downloads=29647 · hf_likes=34 · hf_params=4619184640 · pipeline=text-generation · license=apache-2.0"},{"ref":"E14","kind":"event","title":"arcee-ai/Virtuoso-Small-v2","date":"2025-01-30T05:41:29+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Virtuoso-Small-v2","signal_url":"https://onlylabs.fyi/signals/65d4f427-f0c2-4648-8019-7b07f1a07e4f","signal_json_url":"https://onlylabs.fyi/signals/65d4f427-f0c2-4648-8019-7b07f1a07e4f/signal.json","text":"model_released · arcee-ai/Virtuoso-Small-v2 · signal_desk=releases · occurred_at=2025-01-30T05:41:29+00:00 · url=https://huggingface.co/arcee-ai/Virtuoso-Small-v2 · hf_downloads=1251 · hf_likes=35 · hf_params=14765947904 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E15","kind":"event","title":"Technical AI Account Manager","date":"2026-05-22T14:15:42+00:00","date_source":"greenhouse.updated_at","source_url":"https://www.arcee.ai/careers?gh_jid=5229012008","signal_url":"https://onlylabs.fyi/signals/db9d7227-db02-4008-bed9-862d9f43f94b","signal_json_url":"https://onlylabs.fyi/signals/db9d7227-db02-4008-bed9-862d9f43f94b/signal.json","text":"job_opened · Technical AI Account Manager · signal_desk=hiring · occurred_at=2026-05-22T14:15:42+00:00 · url=https://www.arcee.ai/careers?gh_jid=5229012008 · raw={\"location\":\"SF, CA\",\"ats\":\"greenhouse\"}"},{"ref":"E16","kind":"event","title":"Compute Infrastructure Specialist","date":"2026-05-22T14:08:28+00:00","date_source":"greenhouse.updated_at","source_url":"https://www.arcee.ai/careers?gh_jid=5228121008","signal_url":"https://onlylabs.fyi/signals/5d846be1-457d-41c6-8868-b134f1ee8976","signal_json_url":"https://onlylabs.fyi/signals/5d846be1-457d-41c6-8868-b134f1ee8976/signal.json","text":"job_opened · Compute Infrastructure Specialist · signal_desk=hiring · occurred_at=2026-05-22T14:08:28+00:00 · url=https://www.arcee.ai/careers?gh_jid=5228121008 · raw={\"location\":\"SF, CA\",\"ats\":\"greenhouse\"}"},{"ref":"E17","kind":"event","title":"arcee-ai/Virtuoso-Large","date":"2025-06-09T17:23:45+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Virtuoso-Large","signal_url":"https://onlylabs.fyi/signals/3a9535a1-b0ed-4bc6-824d-ea39702635ec","signal_json_url":"https://onlylabs.fyi/signals/3a9535a1-b0ed-4bc6-824d-ea39702635ec/signal.json","text":"model_released · arcee-ai/Virtuoso-Large · signal_desk=releases · occurred_at=2025-06-09T17:23:45+00:00 · url=https://huggingface.co/arcee-ai/Virtuoso-Large · hf_downloads=12 · hf_likes=30 · hf_params=72706203648 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E18","kind":"event","title":"arcee-ai/Trinity-Nano-Base","date":"2025-12-01T18:28:08+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Nano-Base","signal_url":"https://onlylabs.fyi/signals/f42fb7c7-bfa3-4215-930c-a7f7f692c5be","signal_json_url":"https://onlylabs.fyi/signals/f42fb7c7-bfa3-4215-930c-a7f7f692c5be/signal.json","text":"model_released · arcee-ai/Trinity-Nano-Base · signal_desk=releases · occurred_at=2025-12-01T18:28:08+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Nano-Base · hf_downloads=2134 · hf_likes=27 · hf_params=6120003328 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E19","kind":"event","title":"arcee-ai/Trinity-Mini-Base","date":"2025-12-01T18:25:42+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Mini-Base","signal_url":"https://onlylabs.fyi/signals/4287d123-891d-413e-ab05-182b0dfc4851","signal_json_url":"https://onlylabs.fyi/signals/4287d123-891d-413e-ab05-182b0dfc4851/signal.json","text":"model_released · arcee-ai/Trinity-Mini-Base · signal_desk=releases · occurred_at=2025-12-01T18:25:42+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Mini-Base · hf_downloads=1896 · hf_likes=22 · hf_params=26123974400 · pipeline=text-generation · license=other · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E20","kind":"event","title":"arcee-ai/Arcee-SuperNova-v1","date":"2025-06-10T07:52:25+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Arcee-SuperNova-v1","signal_url":"https://onlylabs.fyi/signals/3d216abc-b8d7-4742-9587-6e5bd2d41389","signal_json_url":"https://onlylabs.fyi/signals/3d216abc-b8d7-4742-9587-6e5bd2d41389/signal.json","text":"model_released · arcee-ai/Arcee-SuperNova-v1 · signal_desk=releases · occurred_at=2025-06-10T07:52:25+00:00 · url=https://huggingface.co/arcee-ai/Arcee-SuperNova-v1 · hf_downloads=60 · hf_likes=17 · hf_params=70553706496 · pipeline=text-generation · license=llama3 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E21","kind":"event","title":"arcee-ai/DALM","date":"2023-07-31T23:23:58+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/DALM","signal_url":"https://onlylabs.fyi/signals/37fc1d92-f927-44e7-b257-99f2009e6899","signal_json_url":"https://onlylabs.fyi/signals/37fc1d92-f927-44e7-b257-99f2009e6899/signal.json","text":"repo_new · arcee-ai/DALM · signal_desk=repos · occurred_at=2023-07-31T23:23:58+00:00 · url=https://github.com/arcee-ai/DALM · stars=341 · hn=3 points/1 comments · raw={\"repo\":\"arcee-ai/DALM\",\"description\":\"Domain Adapted Language Modeling Toolkit - E2E RAG\",\"language\":\"Python\"}"},{"ref":"E22","kind":"event","title":"arcee-ai/Trinity-Mini-Base-Pre-Anneal","date":"2025-12-11T17:42:16+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Mini-Base-Pre-Anneal","signal_url":"https://onlylabs.fyi/signals/87f44530-ad15-4971-b256-af2eaf6a27ed","signal_json_url":"https://onlylabs.fyi/signals/87f44530-ad15-4971-b256-af2eaf6a27ed/signal.json","text":"model_released · arcee-ai/Trinity-Mini-Base-Pre-Anneal · signal_desk=releases · occurred_at=2025-12-11T17:42:16+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Mini-Base-Pre-Anneal · hf_downloads=111 · hf_likes=14 · hf_params=26123974400 · pipeline=text-generation · license=other"},{"ref":"E23","kind":"event","title":"arcee-ai/AFM-4.5B-Base-KDA-NoPE","date":"2025-12-14T21:35:17+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-Base-KDA-NoPE","signal_url":"https://onlylabs.fyi/signals/b8d9abb6-e894-46ef-9a30-93ce6bcf43fc","signal_json_url":"https://onlylabs.fyi/signals/b8d9abb6-e894-46ef-9a30-93ce6bcf43fc/signal.json","text":"model_released · arcee-ai/AFM-4.5B-Base-KDA-NoPE · signal_desk=releases · occurred_at=2025-12-14T21:35:17+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-Base-KDA-NoPE · hf_downloads=11 · hf_likes=14 · hf_params=4999169436 · pipeline=image-feature-extraction · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E24","kind":"event","title":"arcee-ai/Trinity-Nano-Base-Pre-Anneal","date":"2025-12-11T17:41:51+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Nano-Base-Pre-Anneal","signal_url":"https://onlylabs.fyi/signals/5ec033eb-c521-476c-aad0-fcef9f419b34","signal_json_url":"https://onlylabs.fyi/signals/5ec033eb-c521-476c-aad0-fcef9f419b34/signal.json","text":"model_released · arcee-ai/Trinity-Nano-Base-Pre-Anneal · signal_desk=releases · occurred_at=2025-12-11T17:41:51+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Nano-Base-Pre-Anneal · hf_downloads=213 · hf_likes=13 · hf_params=6120003328 · pipeline=text-generation · license=other"},{"ref":"E25","kind":"event","title":"arcee-ai/AFM-4.5B-Base-KDA-Only","date":"2025-12-14T21:35:04+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-Base-KDA-Only","signal_url":"https://onlylabs.fyi/signals/854622d8-0334-40e4-8706-9c1a05e69792","signal_json_url":"https://onlylabs.fyi/signals/854622d8-0334-40e4-8706-9c1a05e69792/signal.json","text":"model_released · arcee-ai/AFM-4.5B-Base-KDA-Only · signal_desk=releases · occurred_at=2025-12-14T21:35:04+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-Base-KDA-Only · hf_downloads=22 · hf_likes=12 · hf_params=5047140048 · pipeline=image-feature-extraction · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E26","kind":"event","title":"arcee-ai/Caller","date":"2025-06-09T20:41:09+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Caller","signal_url":"https://onlylabs.fyi/signals/32d71ab5-5d2d-40ed-9857-e37fa73ffae0","signal_json_url":"https://onlylabs.fyi/signals/32d71ab5-5d2d-40ed-9857-e37fa73ffae0/signal.json","text":"model_released · arcee-ai/Caller · signal_desk=releases · occurred_at=2025-06-09T20:41:09+00:00 · url=https://huggingface.co/arcee-ai/Caller · hf_downloads=4 · hf_likes=12 · hf_params=32763876352 · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E27","kind":"event","title":"arcee-ai/AFM-4.5B-ov","date":"2025-09-05T09:00:52+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-ov","signal_url":"https://onlylabs.fyi/signals/eb801ada-02cc-44f6-a8e2-69a0a23cb22c","signal_json_url":"https://onlylabs.fyi/signals/eb801ada-02cc-44f6-a8e2-69a0a23cb22c/signal.json","text":"model_released · arcee-ai/AFM-4.5B-ov · signal_desk=releases · occurred_at=2025-09-05T09:00:52+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-ov · hf_likes=8 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E28","kind":"event","title":"arcee-ai/Trinity-Tokenizer","date":"2025-10-08T19:21:56+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/Trinity-Tokenizer","signal_url":"https://onlylabs.fyi/signals/0dbd4135-8570-4464-b3ac-0d956a9ac725","signal_json_url":"https://onlylabs.fyi/signals/0dbd4135-8570-4464-b3ac-0d956a9ac725/signal.json","text":"model_released · arcee-ai/Trinity-Tokenizer · signal_desk=releases · occurred_at=2025-10-08T19:21:56+00:00 · url=https://huggingface.co/arcee-ai/Trinity-Tokenizer · hf_downloads=38 · hf_likes=6 · license=other"},{"ref":"E29","kind":"event","title":"arcee-ai/AFM-4.5B-Preview","date":"2025-06-19T16:36:25+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-Preview","signal_url":"https://onlylabs.fyi/signals/c7dfe681-271c-49dd-b3dc-1916fb395e66","signal_json_url":"https://onlylabs.fyi/signals/c7dfe681-271c-49dd-b3dc-1916fb395e66/signal.json","text":"model_released · arcee-ai/AFM-4.5B-Preview · signal_desk=releases · occurred_at=2025-06-19T16:36:25+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-Preview · hf_downloads=12 · hf_likes=5 · hf_params=4619491840 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E30","kind":"event","title":"arcee-ai/DistillKit","date":"2024-07-31T22:16:09+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/DistillKit","signal_url":"https://onlylabs.fyi/signals/a408cea1-79ee-4127-900a-ebeaad43a8ac","signal_json_url":"https://onlylabs.fyi/signals/a408cea1-79ee-4127-900a-ebeaad43a8ac/signal.json","text":"repo_new · arcee-ai/DistillKit · signal_desk=repos · occurred_at=2024-07-31T22:16:09+00:00 · url=https://github.com/arcee-ai/DistillKit · stars=960 · raw={\"repo\":\"arcee-ai/DistillKit\",\"description\":\"An Open Source Toolkit For LLM Distillation\",\"language\":\"Python\"}"},{"ref":"E31","kind":"event","title":"arcee-ai/DeepSeek-V3-0324-bf16","date":"2025-03-24T15:18:33+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/DeepSeek-V3-0324-bf16","signal_url":"https://onlylabs.fyi/signals/02c5195e-6add-43c5-969a-2d3b9d01b62a","signal_json_url":"https://onlylabs.fyi/signals/02c5195e-6add-43c5-969a-2d3b9d01b62a/signal.json","text":"model_released · arcee-ai/DeepSeek-V3-0324-bf16 · signal_desk=releases · occurred_at=2025-03-24T15:18:33+00:00 · url=https://huggingface.co/arcee-ai/DeepSeek-V3-0324-bf16 · hf_downloads=17 · hf_likes=3 · hf_params=684489845504 · pipeline=text-generation · license=mit"},{"ref":"E32","kind":"event","title":"arcee-ai/AFM-4.5B-Base-Pre-Anneal","date":"2025-05-27T19:06:11+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/AFM-4.5B-Base-Pre-Anneal","signal_url":"https://onlylabs.fyi/signals/f34d3cab-c773-4142-b49f-64412e91c5f9","signal_json_url":"https://onlylabs.fyi/signals/f34d3cab-c773-4142-b49f-64412e91c5f9/signal.json","text":"model_released · arcee-ai/AFM-4.5B-Base-Pre-Anneal · signal_desk=releases · occurred_at=2025-05-27T19:06:11+00:00 · url=https://huggingface.co/arcee-ai/AFM-4.5B-Base-Pre-Anneal · hf_downloads=6 · hf_likes=3 · hf_params=4620474880 · pipeline=text-generation · license=apache-2.0"},{"ref":"E33","kind":"event","title":"arcee-ai/fastmlx","date":"2024-03-29T18:33:55+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/fastmlx","signal_url":"https://onlylabs.fyi/signals/80898ce5-e398-461c-87f6-f0f028b1c078","signal_json_url":"https://onlylabs.fyi/signals/80898ce5-e398-461c-87f6-f0f028b1c078/signal.json","text":"repo_new · arcee-ai/fastmlx · signal_desk=repos · occurred_at=2024-03-29T18:33:55+00:00 · url=https://github.com/arcee-ai/fastmlx · stars=358 · raw={\"repo\":\"arcee-ai/fastmlx\",\"description\":\"FastMLX is a high performance production ready API to host MLX models.\",\"language\":\"Python\"}"},{"ref":"E34","kind":"event","title":"arcee-ai/PruneMe","date":"2024-04-10T22:34:25+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/PruneMe","signal_url":"https://onlylabs.fyi/signals/889a944d-df4e-400f-8727-c9adee77555c","signal_json_url":"https://onlylabs.fyi/signals/889a944d-df4e-400f-8727-c9adee77555c/signal.json","text":"repo_new · arcee-ai/PruneMe · signal_desk=repos · occurred_at=2024-04-10T22:34:25+00:00 · url=https://github.com/arcee-ai/PruneMe · stars=267 · raw={\"repo\":\"arcee-ai/PruneMe\",\"description\":\"Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models\",\"language\":\"Python\"}"},{"ref":"E35","kind":"event","title":"arcee-ai/EvolKit","date":"2024-08-07T11:04:05+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/EvolKit","signal_url":"https://onlylabs.fyi/signals/e82b6c94-1f4b-493f-83de-236750989554","signal_json_url":"https://onlylabs.fyi/signals/e82b6c94-1f4b-493f-83de-236750989554/signal.json","text":"repo_new · arcee-ai/EvolKit · signal_desk=repos · occurred_at=2024-08-07T11:04:05+00:00 · url=https://github.com/arcee-ai/EvolKit · stars=257 · raw={\"repo\":\"arcee-ai/EvolKit\",\"description\":\"EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Models (LLMs). \",\"language\":\"Jupyter Notebook\"}"},{"ref":"E36","kind":"event","title":"arcee-ai/arcee-blitz-caller-beta","date":"2025-02-21T06:53:45+00:00","date_source":"source","source_url":"https://huggingface.co/arcee-ai/arcee-blitz-caller-beta","signal_url":"https://onlylabs.fyi/signals/f4b6b1a3-c261-448d-af63-60341d612f77","signal_json_url":"https://onlylabs.fyi/signals/f4b6b1a3-c261-448d-af63-60341d612f77/signal.json","text":"model_released · arcee-ai/arcee-blitz-caller-beta · signal_desk=releases · occurred_at=2025-02-21T06:53:45+00:00 · url=https://huggingface.co/arcee-ai/arcee-blitz-caller-beta · hf_downloads=5 · hf_likes=1 · hf_params=23572423680 · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E37","kind":"event","title":"arcee-ai/trinity-large-tech-report","date":"2026-01-27T20:08:46+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/trinity-large-tech-report","signal_url":"https://onlylabs.fyi/signals/8e750f42-1a87-42cd-a42a-bcb1acb363a5","signal_json_url":"https://onlylabs.fyi/signals/8e750f42-1a87-42cd-a42a-bcb1acb363a5/signal.json","text":"repo_new · arcee-ai/trinity-large-tech-report · signal_desk=repos · occurred_at=2026-01-27T20:08:46+00:00 · url=https://github.com/arcee-ai/trinity-large-tech-report · stars=124 · raw={\"repo\":\"arcee-ai/trinity-large-tech-report\"}"},{"ref":"E38","kind":"event","title":"arcee-ai/pybubble","date":"2025-11-16T04:37:22+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/pybubble","signal_url":"https://onlylabs.fyi/signals/6f498857-818f-43d8-904c-d7bfd27e8812","signal_json_url":"https://onlylabs.fyi/signals/6f498857-818f-43d8-904c-d7bfd27e8812/signal.json","text":"repo_new · arcee-ai/pybubble · signal_desk=repos · occurred_at=2025-11-16T04:37:22+00:00 · url=https://github.com/arcee-ai/pybubble · stars=80 · raw={\"repo\":\"arcee-ai/pybubble\",\"language\":\"Python\"}"},{"ref":"E39","kind":"event","title":"arcee-ai/DAM","date":"2024-08-13T03:42:28+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/DAM","signal_url":"https://onlylabs.fyi/signals/bbe412c7-a4bf-41ae-899b-764024b73e3d","signal_json_url":"https://onlylabs.fyi/signals/bbe412c7-a4bf-41ae-899b-764024b73e3d/signal.json","text":"repo_new · arcee-ai/DAM · signal_desk=repos · occurred_at=2024-08-13T03:42:28+00:00 · url=https://github.com/arcee-ai/DAM · stars=56 · raw={\"repo\":\"arcee-ai/DAM\",\"language\":\"Python\"}"},{"ref":"E40","kind":"event","title":"arcee-ai/arcee-python","date":"2023-06-08T21:52:18+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/arcee-python","signal_url":"https://onlylabs.fyi/signals/906c20c0-e36f-4ad8-98a8-9fad5f23d63b","signal_json_url":"https://onlylabs.fyi/signals/906c20c0-e36f-4ad8-98a8-9fad5f23d63b/signal.json","text":"repo_new · arcee-ai/arcee-python · signal_desk=repos · occurred_at=2023-06-08T21:52:18+00:00 · url=https://github.com/arcee-ai/arcee-python · stars=28 · raw={\"repo\":\"arcee-ai/arcee-python\",\"description\":\"The Arcee client for executing domain-adpated language model routines https://pypi.org/project/arcee-py/\",\"language\":\"Python\"}"},{"ref":"E41","kind":"event","title":"arcee-ai/KidRails","date":"2025-02-11T16:28:50+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/KidRails","signal_url":"https://onlylabs.fyi/signals/fc91b138-d32e-46c7-8054-eb93385cd631","signal_json_url":"https://onlylabs.fyi/signals/fc91b138-d32e-46c7-8054-eb93385cd631/signal.json","text":"repo_new · arcee-ai/KidRails · signal_desk=repos · occurred_at=2025-02-11T16:28:50+00:00 · url=https://github.com/arcee-ai/KidRails · stars=16 · raw={\"repo\":\"arcee-ai/KidRails\",\"language\":\"Python\"}"},{"ref":"E42","kind":"event","title":"arcee-ai/NeMo-RL","date":"2025-08-14T00:08:13+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/NeMo-RL","signal_url":"https://onlylabs.fyi/signals/826f1087-1cc4-4dc9-903a-4a76f26d92ed","signal_json_url":"https://onlylabs.fyi/signals/826f1087-1cc4-4dc9-903a-4a76f26d92ed/signal.json","text":"repo_new · arcee-ai/NeMo-RL · signal_desk=repos · occurred_at=2025-08-14T00:08:13+00:00 · url=https://github.com/arcee-ai/NeMo-RL · stars=12 · raw={\"repo\":\"arcee-ai/NeMo-RL\",\"description\":\"Scalable toolkit for efficient model reinforcement\",\"language\":\"Python\"}"},{"ref":"E43","kind":"event","title":"arcee-ai/code-llama-rag","date":"2023-09-28T14:44:56+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/code-llama-rag","signal_url":"https://onlylabs.fyi/signals/33e39836-0519-47c4-9ab0-10e2877f7032","signal_json_url":"https://onlylabs.fyi/signals/33e39836-0519-47c4-9ab0-10e2877f7032/signal.json","text":"repo_new · arcee-ai/code-llama-rag · signal_desk=repos · occurred_at=2023-09-28T14:44:56+00:00 · url=https://github.com/arcee-ai/code-llama-rag · stars=12 · raw={\"repo\":\"arcee-ai/code-llama-rag\",\"description\":\"The first RAG retriever tuned particularly for code and code Llama\",\"language\":\"Python\"}"},{"ref":"E44","kind":"event","title":"arcee-ai/anymcp","date":"2025-05-06T09:20:06+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/anymcp","signal_url":"https://onlylabs.fyi/signals/69136e4e-afb2-4e3f-8562-c6385d01b2bf","signal_json_url":"https://onlylabs.fyi/signals/69136e4e-afb2-4e3f-8562-c6385d01b2bf/signal.json","text":"repo_new · arcee-ai/anymcp · signal_desk=repos · occurred_at=2025-05-06T09:20:06+00:00 · url=https://github.com/arcee-ai/anymcp · stars=8 · raw={\"repo\":\"arcee-ai/anymcp\",\"language\":\"Python\"}"},{"ref":"E45","kind":"event","title":"arcee-ai/aws-samples","date":"2024-09-03T13:42:00+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/aws-samples","signal_url":"https://onlylabs.fyi/signals/8d7236ba-b800-4c7f-ad58-5def8f3ae0f3","signal_json_url":"https://onlylabs.fyi/signals/8d7236ba-b800-4c7f-ad58-5def8f3ae0f3/signal.json","text":"repo_new · arcee-ai/aws-samples · signal_desk=repos · occurred_at=2024-09-03T13:42:00+00:00 · url=https://github.com/arcee-ai/aws-samples · stars=8 · raw={\"repo\":\"arcee-ai/aws-samples\",\"description\":\"Developer resources to work with Arcee models on AWS\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E46","kind":"event","title":"arcee-ai/Model-Tools","date":"2024-03-27T22:58:51+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/Model-Tools","signal_url":"https://onlylabs.fyi/signals/b497ce17-75ed-4f8b-9be0-d7a73568c031","signal_json_url":"https://onlylabs.fyi/signals/b497ce17-75ed-4f8b-9be0-d7a73568c031/signal.json","text":"repo_new · arcee-ai/Model-Tools · signal_desk=repos · occurred_at=2024-03-27T22:58:51+00:00 · url=https://github.com/arcee-ai/Model-Tools · stars=6 · raw={\"repo\":\"arcee-ai/Model-Tools\",\"language\":\"Python\"}"},{"ref":"E47","kind":"event","title":"arcee-ai/arcee-trainium-recipes","date":"2024-02-01T18:11:31+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/arcee-trainium-recipes","signal_url":"https://onlylabs.fyi/signals/78fe9812-c3f1-4d99-83f5-2d9722c00bc9","signal_json_url":"https://onlylabs.fyi/signals/78fe9812-c3f1-4d99-83f5-2d9722c00bc9/signal.json","text":"repo_new · arcee-ai/arcee-trainium-recipes · signal_desk=repos · occurred_at=2024-02-01T18:11:31+00:00 · url=https://github.com/arcee-ai/arcee-trainium-recipes · stars=4 · raw={\"repo\":\"arcee-ai/arcee-trainium-recipes\",\"description\":\"The repository contains all the set-up required to execute trainium training jobs. \",\"language\":\"Python\"}"},{"ref":"E48","kind":"event","title":"arcee-ai/notebooks","date":"2023-10-04T19:37:31+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/notebooks","signal_url":"https://onlylabs.fyi/signals/23c96696-5c61-42d5-b1ea-6211bb33a017","signal_json_url":"https://onlylabs.fyi/signals/23c96696-5c61-42d5-b1ea-6211bb33a017/signal.json","text":"repo_new · arcee-ai/notebooks · signal_desk=repos · occurred_at=2023-10-04T19:37:31+00:00 · url=https://github.com/arcee-ai/notebooks · stars=4 · raw={\"repo\":\"arcee-ai/notebooks\",\"description\":\"Demo Notebooks showcasing Arcee and DALM\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E49","kind":"event","title":"arcee-ai/token.js","date":"2025-02-11T03:09:39+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/token.js","signal_url":"https://onlylabs.fyi/signals/f3e69798-2c5d-4ffe-b093-6fcccaf8ed63","signal_json_url":"https://onlylabs.fyi/signals/f3e69798-2c5d-4ffe-b093-6fcccaf8ed63/signal.json","text":"repo_forked · arcee-ai/token.js · signal_desk=forks · occurred_at=2025-02-11T03:09:39+00:00 · url=https://github.com/arcee-ai/token.js · stars=3 · raw={\"repo\":\"arcee-ai/token.js\",\"parent\":\"token-js/token.js\"}"},{"ref":"E50","kind":"event","title":"arcee-ai/entropix","date":"2024-10-14T23:02:30+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/entropix","signal_url":"https://onlylabs.fyi/signals/c9ea6498-8bac-4851-97b3-b6b4c5750071","signal_json_url":"https://onlylabs.fyi/signals/c9ea6498-8bac-4851-97b3-b6b4c5750071/signal.json","text":"repo_forked · arcee-ai/entropix · signal_desk=forks · occurred_at=2024-10-14T23:02:30+00:00 · url=https://github.com/arcee-ai/entropix · stars=3 · raw={\"repo\":\"arcee-ai/entropix\",\"parent\":\"xjdr-alt/entropix\"}"},{"ref":"E51","kind":"event","title":"arcee-ai/optillm","date":"2024-10-04T03:04:29+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/optillm","signal_url":"https://onlylabs.fyi/signals/4819afbd-8628-408a-80b8-64b79c40f0f8","signal_json_url":"https://onlylabs.fyi/signals/4819afbd-8628-408a-80b8-64b79c40f0f8/signal.json","text":"repo_forked · arcee-ai/optillm · signal_desk=forks · occurred_at=2024-10-04T03:04:29+00:00 · url=https://github.com/arcee-ai/optillm · stars=3 · raw={\"repo\":\"arcee-ai/optillm\",\"parent\":\"algorithmicsuperintelligence/optillm\"}"},{"ref":"E52","kind":"event","title":"arcee-ai/optillm-upstream","date":"2024-10-24T23:39:59+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/optillm-upstream","signal_url":"https://onlylabs.fyi/signals/11fb9a0b-83cd-473e-881a-936154cdae66","signal_json_url":"https://onlylabs.fyi/signals/11fb9a0b-83cd-473e-881a-936154cdae66/signal.json","text":"repo_forked · arcee-ai/optillm-upstream · signal_desk=forks · occurred_at=2024-10-24T23:39:59+00:00 · url=https://github.com/arcee-ai/optillm-upstream · stars=2 · raw={\"repo\":\"arcee-ai/optillm-upstream\",\"parent\":\"algorithmicsuperintelligence/optillm\"}"},{"ref":"E53","kind":"event","title":"arcee-ai/dify-playground-frontendd","date":"2024-10-24T19:12:17+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/dify-playground-frontendd","signal_url":"https://onlylabs.fyi/signals/994201ed-dbf7-46ec-ab1e-417e4d1bc2dc","signal_json_url":"https://onlylabs.fyi/signals/994201ed-dbf7-46ec-ab1e-417e4d1bc2dc/signal.json","text":"repo_forked · arcee-ai/dify-playground-frontendd · signal_desk=forks · occurred_at=2024-10-24T19:12:17+00:00 · url=https://github.com/arcee-ai/dify-playground-frontendd · stars=2 · raw={\"repo\":\"arcee-ai/dify-playground-frontendd\",\"parent\":\"langgenius/dify\"}"},{"ref":"E54","kind":"event","title":"arcee-ai/Megatron-LM-Llama-70B","date":"2024-05-22T17:40:11+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/Megatron-LM-Llama-70B","signal_url":"https://onlylabs.fyi/signals/ca2a6f89-1577-4bdf-9f9f-b5c3c87b3c19","signal_json_url":"https://onlylabs.fyi/signals/ca2a6f89-1577-4bdf-9f9f-b5c3c87b3c19/signal.json","text":"repo_forked · arcee-ai/Megatron-LM-Llama-70B · signal_desk=forks · occurred_at=2024-05-22T17:40:11+00:00 · url=https://github.com/arcee-ai/Megatron-LM-Llama-70B · stars=2 · raw={\"repo\":\"arcee-ai/Megatron-LM-Llama-70B\",\"parent\":\"NVIDIA/Megatron-LM\"}"},{"ref":"E55","kind":"event","title":"arcee-ai/llm-autoeval","date":"2024-02-28T03:16:00+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/llm-autoeval","signal_url":"https://onlylabs.fyi/signals/ce5c87c6-b574-45a9-bbee-e4d5bfa7c199","signal_json_url":"https://onlylabs.fyi/signals/ce5c87c6-b574-45a9-bbee-e4d5bfa7c199/signal.json","text":"repo_forked · arcee-ai/llm-autoeval · signal_desk=forks · occurred_at=2024-02-28T03:16:00+00:00 · url=https://github.com/arcee-ai/llm-autoeval · stars=2 · raw={\"repo\":\"arcee-ai/llm-autoeval\",\"parent\":\"mlabonne/llm-autoeval\"}"},{"ref":"E56","kind":"event","title":"arcee-ai/pipelines","date":"2025-02-17T16:02:04+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/pipelines","signal_url":"https://onlylabs.fyi/signals/739cdf1f-418d-457c-8c03-f211d133d002","signal_json_url":"https://onlylabs.fyi/signals/739cdf1f-418d-457c-8c03-f211d133d002/signal.json","text":"repo_forked · arcee-ai/pipelines · signal_desk=forks · occurred_at=2025-02-17T16:02:04+00:00 · url=https://github.com/arcee-ai/pipelines · stars=1 · raw={\"repo\":\"arcee-ai/pipelines\",\"parent\":\"open-webui/pipelines\"}"},{"ref":"E57","kind":"event","title":"arcee-ai/open-instruct","date":"2024-12-11T23:54:41+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/open-instruct","signal_url":"https://onlylabs.fyi/signals/9d00ab53-6cd6-4142-8abe-01bfec477f76","signal_json_url":"https://onlylabs.fyi/signals/9d00ab53-6cd6-4142-8abe-01bfec477f76/signal.json","text":"repo_forked · arcee-ai/open-instruct · signal_desk=forks · occurred_at=2024-12-11T23:54:41+00:00 · url=https://github.com/arcee-ai/open-instruct · stars=1 · raw={\"repo\":\"arcee-ai/open-instruct\",\"parent\":\"allenai/open-instruct\"}"},{"ref":"E58","kind":"event","title":"arcee-ai/chat-ui","date":"2024-08-19T14:57:12+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/chat-ui","signal_url":"https://onlylabs.fyi/signals/bcf97310-e009-4f16-befe-2771aadc0bf2","signal_json_url":"https://onlylabs.fyi/signals/bcf97310-e009-4f16-befe-2771aadc0bf2/signal.json","text":"repo_forked · arcee-ai/chat-ui · signal_desk=forks · occurred_at=2024-08-19T14:57:12+00:00 · url=https://github.com/arcee-ai/chat-ui · stars=1 · raw={\"repo\":\"arcee-ai/chat-ui\",\"parent\":\"huggingface/chat-ui\"}"},{"ref":"E59","kind":"event","title":"arcee-ai/Pai-Megatron-Patch-Llama3-70B","date":"2024-05-19T06:01:51+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/Pai-Megatron-Patch-Llama3-70B","signal_url":"https://onlylabs.fyi/signals/7706f2d3-6244-4804-9dc2-35b7b18da0f8","signal_json_url":"https://onlylabs.fyi/signals/7706f2d3-6244-4804-9dc2-35b7b18da0f8/signal.json","text":"repo_forked · arcee-ai/Pai-Megatron-Patch-Llama3-70B · signal_desk=forks · occurred_at=2024-05-19T06:01:51+00:00 · url=https://github.com/arcee-ai/Pai-Megatron-Patch-Llama3-70B · stars=1 · raw={\"repo\":\"arcee-ai/Pai-Megatron-Patch-Llama3-70B\",\"parent\":\"alibaba/Pai-Megatron-Patch\"}"},{"ref":"E60","kind":"event","title":"arcee-ai/prime-rl","date":"2025-11-11T00:08:20+00:00","date_source":"source","source_url":"https://github.com/arcee-ai/prime-rl","signal_url":"https://onlylabs.fyi/signals/8da333a0-40e4-4208-b8bb-5cdd92073433","signal_json_url":"https://onlylabs.fyi/signals/8da333a0-40e4-4208-b8bb-5cdd92073433/signal.json","text":"repo_forked · arcee-ai/prime-rl · signal_desk=forks · occurred_at=2025-11-11T00:08:20+00:00 · url=https://github.com/arcee-ai/prime-rl · raw={\"repo\":\"arcee-ai/prime-rl\",\"parent\":\"PrimeIntellect-ai/prime-rl\"}"}]}