aws / aws/amazon-sagemaker-feedback
Improve Instruction Fine-Tuning Documentation on AWS Jumpstart
- Dominant language
- No language data
- Stars
- 10
- Forks
- 3
- PR merge metrics
- No merged PRs in 30d
Description
### Product Category
JumpStart
### Feedback Category
Clarity and Comprehensibility, Missing Examples and Tutorials
### Reference Link
_No response_
### Details
It would be beneficial to clearly state if pre-processing of samples is necessary (any special tokens that need to be inserted for Mixtral 8x7b) / how the expected samples should look like. Also, the layout is messed up.
Contributor guide
Research direction
Start by locating the AWS JumpStart instruction fine-tuning documentation for Mixtral 8x7b and inspect its current layout and sample guidance. Clarify whether preprocessing and special tokens are required, show the expected sample format, and correct the layout; done means the page answers these questions clearly and renders properly.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100