Update README.md

README.md

@@ -211,6 +211,8 @@ ChatCompletionMessage(
 
 The model is using ***grounded system prompt*** for tool planning. <u>We do not recommend changing it too much, as this may cause hallucinations!</u>
 
+But you can try to add first message as `system` role with additional system rules in your chat history and it adds at the end of this ***grounded system prompt***.
+
 ```
 <|im_start|>system
 You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
@@ -262,9 +264,9 @@ Each tool is represented as a JSON object with fields like "name", "description"
   ...
 ]</tool_call><|im_end|> 
 ```
-`tool_call_id` is local tool id.
-`tool_name` is name of tool(function) calling.
-It contains in `assistant` in 'tool_calls' field.
+`tool_call_id` is local tool id.<br>
+`tool_name` is name of tool(function) calling.<br>
+It contains in `assistant` in `tool_calls` field.<br>
 
 - Responses from tools are located between `<tool_response>`...*all last locals tools*...`</tool_response>`. Every local tool contains separately in specific role `tool`:
 ```python
@@ -714,16 +716,18 @@ Thats great! Okey, can you provide weather in Krasnodar, Moscow and only the sun
 
 ## Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+This model just 7B version of Qwen2.5 and some hallucinations are possible. If you find something interesting in model behavior, please create [issue and lets discuss it!](https://huggingface.co/Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning/discussions) 
 
-[More Information Needed]
+* The model the most stability works in `greedy search` or low `temperature(about < 0.5)`
+* The model can feel some problems with long user plan. It confuses the trajectory of calls and changes the order in which related tasks are performed. In fact, this is not a mistake, but a violation of the user's requirement.
+* The model can solve very easy tasks on the fly, right in the process of calls (for example, basic arithmetic).
 
 
 ## Evaluation
 
-*BFCL benchmark*
+*BFCL benchmark* <br>
 [More Information Needed]
 
 ## Authors
 
-[More Information Needed]
+[Dmitry Tishencko, Vikhrmodels](https://huggingface.co/DiTy)