Changed Groq logo to black color version#1
Closed
cho-groq wants to merge 52 commits into
Closed
Conversation
- Changed the default model in load_config from `mixtral-8x7b-32768` to `llama3-8b-8192`, aligning with the latest model updates available in the Groq API.
- Added handling for JSON formatted responses, including new error checking and response formatting in the post method. - Improved error handling to better manage exceptions and ensure cleaner termination of the loading animation. - Introduced a seed parameter in data preparation for requests, supporting reproducibility in model responses.
- Added support for JSON formatted output and a seed parameter in the run methods of both Chat and Text classes. - Included a check to prevent JSON mode and streaming from being used together, as well as stop sequences and JSON mode, ensuring that feature constraints are respected. - Streamlined user input handling and system prompt inclusion, enhancing the interaction flow and usability. - Added exit/quit syntax to the start of the conversation. - Added goodbye syntax to the end of the conversation.
- Removed whitespace.
- Updated the command-line interface to handle new flags for JSON output (--json) and seed (--seed). - Expanded the help descriptions to include new features and provide clear usage instructions for the added functionalities.
- The README has been comprehensively updated to reflect the enhanced capabilities of the Groq AI Toolkit, including support for JSON formatted responses, the introduction of new models, and the inclusion of a seed for deterministic outputs. - Updated performance metrics from 300 tokens/sec to 800 tokens/sec, showcasing the improved efficiency of the toolkit. - Added descriptions of new features, installation steps, configuration options, and usage scenarios to guide both new and existing users in leveraging the toolkit effectively.
This update enhances the Groq AI Toolkit with additional features, improved error handling, and expanded functionality, particularly introducing support for 'LLama 3', JSON mode, and Seed sampling.
- Update to v1.0.1
- Changed default model in docs to "llama-3.1-8b-instant". - Added support for the following models: 1. `llama-3.1-70b-versatile` 2. `llama-3.1-8b-instant` 3. `llava-v1.5-7b-4096-preview` 4. `llama-guard-3-8b` 5. `gemma2-9b-it` - Added note about 8k token limit for preview models.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.