Update README.md

.gitattributes

@@ -44,4 +44,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+assets/Skiing.mp4 filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -20,12 +20,14 @@ tags:
 - realtime speech conversation
 - asr
 - tts
+base_model:
+- openbmb/MiniCPM-o-2_6
 ---
 
 <h1>A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone</h1>
 
 ## MiniCPM-o 2.6 int4
-This is the int4 quantized version of [**MiniCPM-o 2.6**](https://modelscope.cn/models/OpenBMB/MiniCPM-o-2_6).   
+This is the int4 quantized version of [**MiniCPM-o 2.6**](https://huggingface.co/openbmb/MiniCPM-o-2_6).   
 Running with int4 version would use lower GPU memory (about 9GB).
 
 ### Prepare code and install AutoGPTQ
@@ -66,4 +68,4 @@ model.init_tts()
 
 ```
 
-Usage reference [MiniCPM-o-2_6](https://modelscope.cn/models/OpenBMB/MiniCPM-o-2_6) Usage section.
+Usage reference [MiniCPM-o-2_6#usage](https://huggingface.co/openbmb/MiniCPM-o-2_6#usage)

modeling_minicpmo.py

@@ -378,7 +378,7 @@ class MiniCPMO(MiniCPMOPreTrainedModel):
             vllm_embedding = self.llm.model.embed_tokens(data["input_ids"])
 
         new_vllm_embedding = vllm_embedding.clone()
-        
+
         vision_hidden_states = [
             i.type(vllm_embedding.dtype) if isinstance(i, torch.Tensor) else i for i in vision_hidden_states
         ]