Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,35 +29,6 @@ creation of synthetic datasets.
|
|
| 29 |
- **Taxonomy Repository**: A structured repository where users can
|
| 30 |
submit and manage their contributions of skills and knowledge.
|
| 31 |
|
| 32 |
-
**Core Components**:
|
| 33 |
-
1. **ilab CLI Tool**: Facilitates model interaction, training, and
|
| 34 |
-
data generation.
|
| 35 |
-
2. **Taxonomy Tree**: Organizes skills and knowledge contributions for
|
| 36 |
-
model tuning.
|
| 37 |
-
3. **Community Collaboration**: Encourages open-source contributions,
|
| 38 |
-
including new features, bug fixes, and documentation improvements.
|
| 39 |
-
|
| 40 |
-
**Granite and Merlinite Models**:
|
| 41 |
-
- **Merlinite**: Merlinite is instruct-tuned from the Mistral model,
|
| 42 |
-
providing overall better accuracy than Mistral. It is continuously
|
| 43 |
-
improved using user-submitted data from the taxonomy repository,
|
| 44 |
-
incorporating both skills and knowledge.
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
- **Granite**: [Granite](https://huggingface.co/ibm-granite/granite-7b-base)
|
| 48 |
-
is a base model developed from scratch by IBM Research, trained on 2 trillion
|
| 49 |
-
tokens. The datasets the model was trained on are openly cited in [its
|
| 50 |
-
HuggingFace model card](https://huggingface.co/ibm-granite/granite-7b-base).
|
| 51 |
-
|
| 52 |
-
**Installation and Usage**:
|
| 53 |
-
- [Detailed instructions are available for setting up the `ilab` CLI
|
| 54 |
-
tool](https://github.com/instructlab/instructlab) on various operating systems. Key steps include installing
|
| 55 |
-
necessary dependencies, creating a virtual environment, and
|
| 56 |
-
initializing the `ilab` tool.
|
| 57 |
-
- The CLI supports commands for chatting with models, generating
|
| 58 |
-
synthetic data, downloading pre-trained models, and training models
|
| 59 |
-
with user-generated data.
|
| 60 |
-
|
| 61 |
**Community and Contribution**:
|
| 62 |
- InstructLab welcomes contributions from the open-source community.
|
| 63 |
Users can submit pull requests to the taxonomy repository, participate
|
|
@@ -65,13 +36,6 @@ in discussions, and contribute to ongoing development.
|
|
| 65 |
- The project maintains [a comprehensive guide for contributors](https://github.com/instructlab/community),
|
| 66 |
outlining best practices and governance.
|
| 67 |
|
| 68 |
-
**Getting Started**:
|
| 69 |
-
1. **Install ilab CLI**: Follow the installation instructions specific
|
| 70 |
-
to your operating system.
|
| 71 |
-
2. **Initialize ilab**: Set up the local environment and clone the
|
| 72 |
-
taxonomy repository.
|
| 73 |
-
3. **Contribute**: Create and submit new skills and knowledge to improve LLMs.
|
| 74 |
-
|
| 75 |
**Repository Links**:
|
| 76 |
- [InstructLab Main Repository](https://github.com/instructlab/instructlab)
|
| 77 |
- [Taxonomy Repository](https://github.com/instructlab/taxonomy)
|
|
|
|
| 29 |
- **Taxonomy Repository**: A structured repository where users can
|
| 30 |
submit and manage their contributions of skills and knowledge.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
**Community and Contribution**:
|
| 33 |
- InstructLab welcomes contributions from the open-source community.
|
| 34 |
Users can submit pull requests to the taxonomy repository, participate
|
|
|
|
| 36 |
- The project maintains [a comprehensive guide for contributors](https://github.com/instructlab/community),
|
| 37 |
outlining best practices and governance.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
**Repository Links**:
|
| 40 |
- [InstructLab Main Repository](https://github.com/instructlab/instructlab)
|
| 41 |
- [Taxonomy Repository](https://github.com/instructlab/taxonomy)
|