Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 - tool-calling
 - tool-planning
 ---
-# Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning
+# Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1
 
 <!-- Provide a quick summary of what the model is/does. -->
 
@@ -92,12 +92,12 @@ Next, you need to download the model and tokenizer:
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model = AutoModelForCausalLM.from_pretrained(
-    "Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning",
+    "Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1",
     device_map="auto",
     torch_dtype=torch.bfloat16,  # recommended dtype 
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning",
+    "Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1",
 )
 ```
 
@@ -146,7 +146,7 @@ Then our `generated_response` will look like this:
 For corrected work online serving in VLLM you need additionally load [qwen2_tool_parser.py]() and [chat_template.jinja]() from this repository.
 
 ```
-vllm serve Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning \
+vllm serve Vikhrmodels/Qwen2.5-7B-Instruct-Tool-Planning-v0.1 \
 --download-dir "/path/to/cache" \
 --chat-template "/path/to/chat_template.jinja" \
 --tool-parser-plugin "/path/to/qwen2_tool_parser.py" \
@@ -726,8 +726,14 @@ This model just 7B version of Qwen2.5 and some hallucinations are possible. If y
 
 ## Evaluation <a name="eval"></a>
 
-*BFCL benchmark* <br>
-[More Information Needed]
+| Task                      | Acc(%)   |
+|---------------------------|----------|
+| Simple                    | 73.25    |
+| Multiple                  | 93.00    |
+| Parallel                  | 90.00    |
+| Parallel Multiple         | 81.00    |
+| Relevance Detection       | 64.71    |
+| Irrelevance Detection     | 85.72    |
 
 ## Authors