[None][doc] Add more description on EXAONE example #8089
Conversation
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
yechank-nvidia
changed the title
|
/bot run --stage-list "A10-Build_Docs" |
📝 WalkthroughWalkthroughDocumentation updates to EXAONE README: added a note clarifying model-to-flow mappings, restored and expanded usage guidance per model, and replaced placeholder quantization outputs with concrete sample outputs for multiple prompts. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
examples/models/core/exaone/README.md (2)
16-16: Fix formatting inconsistency in table of contents.Missing space after the dash before the bracket.
Apply this diff:
- -[PyTorch flow Quantization](#pytorch-flow-quantization) + - [PyTorch flow Quantization](#pytorch-flow-quantization)
62-62: Fix typo in documentation."Download he" should be "Download the".
Apply this diff:
-Download he HuggingFace checkpoints of EXAONE-4.0 model. Here, we only use the `EXAONE-4.0-32B` model for the example. From EXAONE-4.0 model, we support only on PyTorch flow. +Download the HuggingFace checkpoints of EXAONE-4.0 model. Here, we only use the `EXAONE-4.0-32B` model for the example. From EXAONE-4.0 model, we support only on PyTorch flow.
🧹 Nitpick comments (1)
examples/models/core/exaone/README.md (1)
69-69: Maintain consistent capitalization.For consistency with the rest of the document, use "PyTorch" with capital T.
Apply this diff:
-### Pytorch flow +### PyTorch flow
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
examples/models/core/exaone/README.md(2 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (2)
examples/models/core/exaone/README.md (2)
35-40: LGTM! Clear guidance on model-to-flow mappings.The added note effectively clarifies which EXAONE model variants should use which flow (TRT vs PyTorch), helping users quickly understand the correct approach for their specific model. The structure and formatting are appropriate for documentation.
81-83: Concrete examples improve documentation clarity.The replacement of placeholder output with actual sample generations for multiple prompts helps users understand what to expect from the model. The outputs are realistic and properly formatted.
|
PR_Github #20339 [ run ] triggered by Bot |
|
PR_Github #20339 [ run ] completed with state |
yechank-nvidia
changed the title
|
/bot skip --comment "doc changes" |
|
PR_Github #20432 [ skip ] triggered by Bot |
|
PR_Github #20432 [ skip ] completed with state |
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> Signed-off-by: Faradawn Yang <faradawny@gmail.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> Signed-off-by: Faradawn Yang <faradawny@gmail.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
3 participants
Summary by CodeRabbit