GraphCanon updated 3w · GitHub synced 3w
Decision brief
Dolly is a large language model that can be used for response generation and training, available through Hugging Face and the Databricks Machine Learning Platform.
Good fit when
- If your project requires a robust pre-trained model available via Hugging Face to quickly generate responses without extensive setup or training processes.
- When you are working within the Databricks ecosystem and wish to leverage GPU-powered clusters for enhanced performance and speed during both inference and training.
Avoid when
- If your project requires a local deployment model that does not involve cloud-based tools, as Dolly's optimal use case involves integration with the Databricks platform.
- In instances where immediate access to GPUs is constrained or expensive in your region, since Dolly training and inference are optimized for GPU processing environments.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1127d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- 69 low (69 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install dollySimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Databricks' Dolly is a large language model available for inference via Hugging Face and can be trained using the Databricks Machine Learning Platform.
Capability facts
- Languages
- python
Source: github.language · Aug 1, 2026
Categories
Tags
README
Getting Started with Response Generation
If you'd like to simply test the model without training, the model is available on Hugging Face as databricks/dolly-v2-12b.
To use the model with the transformers library on a machine with A100 GPUs:
from transformers import pipeline
import torch
instruct_pipeline = pipeline(model="databricks/dolly-v2-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
You can then use the pipeline to answer instructions:
instruct_pipeline("Explain to me the difference between nuclear fission and fusion.")
Getting Started with Training
- Add the
dollyrepo to Databricks (under Repos click Add Repo, enterhttps://github.com/databrickslabs/dolly.git, then click Create Repo). - 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_v4orp4d.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). - Open the
train_dollynotebook in the Repo (which is thetrain_dolly.pyfile in the Githubdollyrepo), attach to your GPU cluster, and run all cells. When training finishes, the notebook will save the model under/dbfs/dolly_training.
For agents
This page has a .md twin and JSON over the API.