{"data":{"slug":"databrickslabs-dolly","name":"dolly","tagline":"Databricks' Dolly, a large language model trained on the Databricks Machine Learning Platform","github_url":"https://github.com/databrickslabs/dolly","owner":"databrickslabs","repo":"dolly","owner_avatar_url":"https://avatars.githubusercontent.com/u/49501376?v=4","primary_language":"Python","stars":10808,"forks":1134,"topics":["chatbot","databricks","dolly","gpt"],"archived":false,"github_pushed_at":"2023-06-30T18:36:16+00:00","maintenance_label":"Dormant","stars_delta_30d":3,"url":"https://www.graphcanon.com/tools/databrickslabs-dolly","markdown_url":"https://www.graphcanon.com/tools/databrickslabs-dolly.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/databrickslabs-dolly","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=databrickslabs-dolly","description":"Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform","homepage_url":"https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html","license":"Apache-2.0","open_issues":5,"watchers":134,"ai_summary":"Dolly is a large language model available for inference and training. It can be used to generate responses to instructions and can be trained on the Databricks Machine Learning Platform.","readme_excerpt":"## Getting Started with Response Generation\n\nIf you'd like to simply test the model without training, the model is available on Hugging Face as [databricks/dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b).\n\nTo use the model with the `transformers` library on a machine with A100 GPUs:\n\n```\nfrom transformers import pipeline\nimport torch\n\ninstruct_pipeline = pipeline(model=\"databricks/dolly-v2-12b\", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map=\"auto\")\n```\n\nYou can then use the pipeline to answer instructions:\n\n```\ninstruct_pipeline(\"Explain to me the difference between nuclear fission and fusion.\")\n```\n\n---\n\n## Getting Started with Training\n\n- Add the `dolly` repo to Databricks (under Repos click Add Repo, enter `https://github.com/databrickslabs/dolly.git`, then click Create Repo).\n- Start a `13.x ML (includes Apache Spark 3.4.0, GPU, Scala 2.12)` or later single-node cluster with node type having 8 A100 GPUs (e.g. `Standard_ND96asr_v4` or `p4d.24xlarge`). Note that these instance types may not be available in all regions, or may be difficult to provision. In Databricks, note that you must select the GPU runtime first, and unselect \"Use Photon\", for these instance types to appear (where supported).\n- Open the `train_dolly` notebook in the Repo (which is the `train_dolly.py` file in the Github `dolly` repo), attach to your GPU cluster, and run all cells.  When training finishes, the notebook will save the model under `/dbfs/dolly_training`.","github_created_at":"2023-03-24T16:15:53+00:00","created_at":"2026-07-11T23:08:35.034929+00:00","updated_at":"2026-09-20T04:29:17.098018+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"chatbot","name":"chatbot"},{"slug":"databricks","name":"databricks"},{"slug":"dolly","name":"dolly"},{"slug":"gpt","name":"gpt"}],"trust":{"provenance":{"is_fork":false,"github_id":618511002,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:14:20.960Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1175,"last_release_at":null,"stars_delta_30d":3,"open_issues_delta_30d":-1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":77,"high_count":0,"last_scan_at":"2026-09-18T08:14:22.583Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:14:19.875Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:14:19.875Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:14:19.875Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires A100 GPUs for optimal performance.","Integration with the Databricks Machine Learning Platform is necessary for full functionality."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you need a language model that integrates seamlessly with the Databricks Machine Learning Platform for both training and inference.","If your project requires the use of A100 GPUs and you are working within the Databricks environment.","When you want to leverage the Apache-2.0 license for open-source collaboration and transparency."],"when_not_to_use":["If your infrastructure does not support A100 GPUs or if you are unable to provision the required instance types in your region.","When you prefer not to use the Databricks Machine Learning Platform for your model training and inference needs.","If your project requires a model that is not licensed under Apache-2.0."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:40:36.391Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires A100 GPUs for optimal performance.; Integration with the Databricks Machine Learning Platform is necessary for full functionality."},{"label":"Adopt for","value":"Dolly is a large language model from Databricks, designed for both inference and training on the Databricks Machine Learning Platform. It is accessible via Hugging Face and requires specific GPU configurations for full-f"},{"label":"License detail","value":"Dolly is licensed under the Apache-2.0 license, which is permissive and allows for free use, modification, and distribution of the software."}]}}