Vikhrmodels
/

Qwen2.5-7B-Instruct-Tool-Planning-v0.1

Text Generation

function-calling

text-generation-inference

Model card Files Files and versions Community

DiTy commited on Feb 17

Commit

f1e92e2

·

verified ·

1 Parent(s): 81be807

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -255,7 +255,7 @@ Each tool is represented as a JSON object with fields like "name", "description"
 **About the structure of prompt:**
 - This model always will answer with new tokens: `<|start_response|>`...*text from model*...`<|end_response|>`. This content is the main one for user and it contains in `assistant` in `content` field.
-- This model always starts <u>*thinking*</u> before tool calls with new tokens: `<|start_thinking|>`...*thinking*...<|end_thinking|>. It contains in `assistant` in `tool_plan` field.
 - After <u>*thinking*</u> model starts generate tool calls (function calling) with Qwen2.5 tokens (it can be a multiple/parallel calling too):
 ```
 <tool_call>[

 **About the structure of prompt:**
 - This model always will answer with new tokens: `<|start_response|>`...*text from model*...`<|end_response|>`. This content is the main one for user and it contains in `assistant` in `content` field.
+- This model always starts <u>*thinking*</u> before tool calls with new tokens: `<|start_thinking|>`...*thinking*...`<|end_thinking|>`. It contains in `assistant` in `tool_plan` field.
 - After <u>*thinking*</u> model starts generate tool calls (function calling) with Qwen2.5 tokens (it can be a multiple/parallel calling too):
 ```
 <tool_call>[