Skip to content

docs(config): align example precision and format with spec table #178

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rishi-jat wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

docs(config): align example precision and format with spec table #178

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/config.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,9 +204,9 @@ Here is an example model artifact configuration JSON document:
},
"config": {
"architecture": "transformer",
"format": "pytorch",
"format": "pt",
"paramSize": "8b",
"precision": "fp16",
"precision": "float16",
Comment on lines +207 to +209
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Feb 28, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

While these changes align the example with the specification, they also highlight inconsistencies in other parts of the repository that should be addressed for overall project consistency.

  1. Go source code: The comments in specs-go/v1/config.go are now out of sync with this documentation.
    • The comment for ModelConfig.Format (line 31) still mentions pytorch.
    • The comment for ModelConfig.Precision (line 37) still mentions fp16.
  2. JSON Schema: The schema in schema/config-schema.json could be strengthened to enforce allowed values. For example, the format property could use an enum to list the valid formats ("onnx", "safetensors", "gguf", "pt"). This would help prevent future inconsistencies.

Please consider addressing these related inconsistencies in this PR or a follow-up to improve overall project quality.

"quantization": "gptq",
"capabilities": {
"inputTypes": [
Expand Down
Loading