Yirany commited on
Commit
5422589
β€’
1 Parent(s): 59a3da4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -4
README.md CHANGED
@@ -12,11 +12,16 @@ datasets:
12
 
13
  ## News <!-- omit in toc -->
14
 
15
- * [2024.05.25] MiniCPM-Llama3-V 2.5 now supports streaming outputs and supports customized system prompts. Try it at [here](#usage)!
16
- * [2024.05.25] MiniCPM-Llama3-V 2.5 now supports [Ollama](https://github.com/OpenBMB/ollama/tree/minicpm-v2.5/examples/minicpm-v2.5). Try it now!
17
- * [2024.05.24] We release the [MiniCPM-Llama3-V 2.5 gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf), which supports [llama.cpp](https://github.com/OpenBMB/MiniCPM-V/tree/main?tab=readme-ov-file#inference-with-llamacpp) inference and provides a 6~8 token/s smooth decoding on mobile phones. Try it now!
 
18
  * [2024.05.23] πŸ”₯πŸ”₯πŸ”₯ MiniCPM-V tops GitHub Trending and HuggingFace Trending! Our demo, retweeted by Gradio’s official account is available at [here](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5). Come and try it out!
19
- * [2024.05.23] πŸ” We've released a comprehensive comparison between Phi-3-vision-128k-instruct and MiniCPM-Llama3-V 2.5, including benchmarks evaluations, and multilingual capabilities πŸŒŸπŸ“ŠπŸŒ. Click [here](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/compare_with_phi-3_vision.md) to view more details.
 
 
 
 
20
  * [2024.05.20] We open-soure MiniCPM-Llama3-V 2.5, it has improved OCR capability and supports 30+ languages, representing the first end-side MLLM achieving GPT-4V level performance! We provide [efficient inference](#deployment-on-mobile-phone) and [simple fine-tuning](https://github.com/OpenBMB/MiniCPM-V/blob/main/finetune/readme.md). Try it now!
21
 
22
 
 
12
 
13
  ## News <!-- omit in toc -->
14
 
15
+ #### πŸ“Œ Pinned
16
+
17
+ * [2024.05.25] πŸš€πŸš€πŸš€ MiniCPM-Llama3-V 2.5 now supports [Ollama](https://github.com/OpenBMB/ollama/tree/minicpm-v2.5/examples/minicpm-v2.5) for efficient inference. Try it now!
18
+ * [2024.05.23] πŸ” We've released a comprehensive comparison between Phi-3-vision-128k-instruct and MiniCPM-Llama3-V 2.5, including benchmarks evaluations, multilingual capabilities, and inference efficiency πŸŒŸπŸ“ŠπŸŒπŸš€. Click [here](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/compare_with_phi-3_vision.md) to view more details.
19
  * [2024.05.23] πŸ”₯πŸ”₯πŸ”₯ MiniCPM-V tops GitHub Trending and HuggingFace Trending! Our demo, retweeted by Gradio’s official account is available at [here](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5). Come and try it out!
20
+
21
+ <br>
22
+
23
+ * [2024.05.25] MiniCPM-Llama3-V 2.5 now supports streaming outputs and customized system prompts. Try it at [here](#usage)!
24
+ * [2024.05.24] We release the [MiniCPM-Llama3-V 2.5 gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf), which supports [llama.cpp](https://github.com/OpenBMB/MiniCPM-V/tree/main?tab=readme-ov-file#inference-with-llamacpp) inference and provides a 6~8 token/s smooth decoding on mobile phones. Try it now!
25
  * [2024.05.20] We open-soure MiniCPM-Llama3-V 2.5, it has improved OCR capability and supports 30+ languages, representing the first end-side MLLM achieving GPT-4V level performance! We provide [efficient inference](#deployment-on-mobile-phone) and [simple fine-tuning](https://github.com/OpenBMB/MiniCPM-V/blob/main/finetune/readme.md). Try it now!
26
 
27