-
Notifications
You must be signed in to change notification settings - Fork 2.4k
update sambanova models #8186
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.
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
update sambanova models #8186
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for your contribution! I've reviewed the changes and found a critical issue that needs attention along with some suggestions for improvement.
| }, | ||
| "gpt-oss-120b": { | ||
| maxTokens: 8192, | ||
| contextWindow: 8192, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Critical Issue: There's an inconsistency here - the description states "128k context window" but the contextWindow property is set to 8192 (8K). Could you verify which value is correct and update accordingly?
If the context window is indeed 128K, it should be 131072 (128 * 1024).
| | "Llama-4-Maverick-17B-128E-Instruct" | ||
| | "Llama-3.3-Swallow-70B-Instruct-v0.4" | ||
| | "Qwen3-32B" | ||
| | "gpt-oss-120b" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is gpt-oss-120b the official model name from SambaNova? The naming pattern differs from other models which use proper casing (e.g., "DeepSeek-V3.1"). Should this perhaps be "GPT-OSS-120B" for consistency with the naming convention used by other models?
|
Additionally, here are some other suggestions to consider:
These are non-blocking suggestions, but addressing them would improve the overall quality of the PR. |
daniel-lxs
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you @snova-jorgep !
Related GitHub Issue
#8185
Closes: #
Description
update list of models available in sambanova provider, adding deepseekv3.1 and gpt oss 120b
Test Procedure
open the sambanova model list dropdown
Pre-Submission Checklist
Screenshots / Videos
Documentation Updates
Additional Notes
Get in Touch
jorgepiedrahita_58208
Important
Add
DeepSeek-V3.1andgpt-oss-120bmodels to SambaNova provider insambanova.ts.DeepSeek-V3.1andgpt-oss-120btoSambaNovaModelIdinsambanova.ts.sambaNovaModelsinsambanova.tswith properties forDeepSeek-V3.1andgpt-oss-120b, includingmaxTokens,contextWindow,supportsImages,supportsPromptCache,inputPrice,outputPrice, anddescription.This description was created by
for de032d8. You can customize this summary. It will automatically update as commits are pushed.