Skip to content

Conversation

reymondzzzz
Copy link
Member

No description provided.

@@ -959,6 +959,18 @@
"deepseek-r1-distill/32b/vllm",
"deepseek-r1-distill/70b/vllm"
]
},
"Qwen/Qwen3-235B-A22B": {
"n_ctx": 41000,
Copy link
Member

Choose a reason for hiding this comment

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

why this number? it should be arount 128k as I know

"default_temperature": 0.6,
"scratchpad": "PASSTHROUGH",
"supports_tools": false,
"supports_multimodality": false,
Copy link
Member

Choose a reason for hiding this comment

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

I'm sure it doesnt support multimodality

Copy link
Member Author

Choose a reason for hiding this comment

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

I set false

"supports_reasoning": "deepseek",
"default_temperature": 0.6,
"scratchpad": "PASSTHROUGH",
"supports_tools": false,
Copy link
Member

Choose a reason for hiding this comment

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

this model should have tools

Copy link
Member Author

Choose a reason for hiding this comment

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

will fix

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants