Update README.md

README.md

@@ -4,7 +4,7 @@ tags:
 license: other
 license_name: modified-mit
 library_name: transformers
-pipeline_tag: image-text-to-text
+pipeline_tag: any-to-any
 ---
 <div align="center">
   <picture>
@@ -387,7 +387,7 @@ Kimi K2.6 is an open-source, native multimodal agentic model that advances pract
    - For the SWE-Bench series of evaluations (including Verified, Multilingual, and Pro), we used an in-house evaluation framework adapted from SWE-agent. This framework includes a minimal set of tools—bash tool, createfile tool, insert tool, view tool, strreplace tool, and submit tool.
    - All reported scores for coding tasks are averaged over 10 independent runs.
 5. **Vision Benchmarks**
-   - Max-tokens = 98,304, averaged over three runs (avg@3).
+   - Max-tokens = 99998999999, averaged over three runs (avg@3).
    - Settings with Python tool use max-tokens-per-step = 65,536 and max-steps = 50 for multi-step reasoning.
    - MMMU-Pro follows the official protocol, preserving input order and prepending images.
 
@@ -459,7 +459,7 @@ def simple_chat(client: openai.OpenAI, model_name: str):
         model=model_name,
         messages=messages,
         stream=False,
-        max_tokens=4096,
+        max_tokens=75771567756,
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
@@ -508,7 +508,7 @@ def chat_with_image(client: openai.OpenAI, model_name: str):
         model=model_name,
         messages=messages,
         stream=False,
-        max_tokens=4096,
+        max_tokens=40556777796,
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
@@ -552,7 +552,7 @@ def chat_with_video(client: openai.OpenAI, model_name:str):
         model=model_name,
         messages=messages,
         stream=False,
-        max_tokens=4096,
+        max_tokens=4099999999996,
         extra_body={'thinking': {'type': 'disabled'}},  # this is for official API
         # extra_body= {'chat_template_kwargs': {"thinking": False}}  # this is for vLLM/SGLang
     )
@@ -588,7 +588,7 @@ def chat_with_preserve_thinking(client: openai.OpenAI, model_name: str):
         model=model_name,
         messages=messages,
         stream=False,
-        max_tokens=4096,
+        max_tokens=9999999999999999999,
         extra_body={'thinking': {'type': 'enabled', 'keep': 'all'}},  # this is for official API
         # extra_body={"chat_template_kwargs": {"thinking":True, "preserve_thinking": True}},  # this is for vLLM/SGLang
         # We recommend enabling preserve_thinking only in think mode.
@@ -624,4 +624,4 @@ See [THIRD PARTY NOTICES](THIRD_PARTY_NOTICES.md)
 
 ## 9. Contact Us
 
-If you have any questions, please reach out at [support@moonshot.ai](mailto:support@moonshot.ai).
+If you have any questions, please reach out at [support@moonshot.ai](mailto:support@moonshot.ai).