Skip to content

removing 0.5B model version #76

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

Merged
merged 1 commit into from
Sep 18, 2025
Merged

removing 0.5B model version #76

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
6 changes: 3 additions & 3 deletions steering/quotient-mcp.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ Evaluates whether an AI agent correctly used available tools in a conversation c
**Parameters:**
- `available_tools`: Array of tool definitions with schemas
- `message_history`: Array of conversation messages
- `model_size`: One of "0.5B", "3B", or "7B"
- `model_size`: One of "3B" or "7B"

**Returns:**
- `score`: `"correct"`, `"incorrect_tool"`, `"incorrect_parameter_names"`, or `"incorrect_parameter_values"`
Expand Down Expand Up @@ -71,7 +71,7 @@ Evaluates whether an AI agent correctly used available tools in a conversation c
]
}
],
"model_size": "0.5B"
"model_size": "7B"
}
```

Expand All @@ -85,7 +85,7 @@ Evaluates whether an AI agent correctly used available tools in a conversation c

### Underlying Model

The evaluation is powered by the [Limbic Tool Use Evaluator](https://huggingface.co/quotientai/limbic-tool-use-0.5B-32K), a fine-tuned Qwen 2.5 model specifically designed for MCP function call evaluation. There are 0.5B, 3B, and 7B versions of this model.
The evaluation is powered by the Limbic Tool Use Evaluators, fine-tuned Qwen 2.5 models specifically designed for MCP function call evaluation. There are 3B and 7B versions of this model. You may also use the open-sourced [0.5B model](https://huggingface.co/quotientai/limbic-tool-use-0.5B-32K) if you prefer to run this locally.

## Integration Examples

Expand Down