Update README.md
Browse files
README.md
CHANGED
|
@@ -27,8 +27,13 @@ tags:
|
|
| 27 |
[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [Online Demo](https://minicpm-omni-webdemo-us.modelbest.cn)</a>
|
| 28 |
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## MiniCPM-o 2.6
|
| 31 |
|
|
|
|
| 32 |
**MiniCPM-o 2.6** is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip-400M, Whisper-medium-300M, ChatTTS-200M, and Qwen2.5-7B with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-V 2.6, and introduces new features for real-time speech conversation and multimodal live streaming. Notable features of MiniCPM-o 2.6 include:
|
| 33 |
|
| 34 |
- 🔥 **Leading Visual Capability.**
|
|
@@ -50,6 +55,7 @@ Advancing popular visual capabilites from MiniCPM-V series, MiniCPM-o 2.6 can pr
|
|
| 50 |
MiniCPM-o 2.6 can be easily used in various ways: (1) [llama.cpp](https://github.com/OpenBMB/llama.cpp/blob/minicpm-omni/examples/llava/README-minicpmo2.6.md) support for efficient CPU inference on local devices, (2) [int4](https://huggingface.co/openbmb/MiniCPM-o-2_6-int4) and [GGUF](https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf) format quantized models in 16 sizes, (3) [vLLM](#efficient-inference-with-llamacpp-ollama-vllm) support for high-throughput and memory-efficient inference, (4) fine-tuning on new domains and tasks with [LLaMA-Factory](./docs/llamafactory_train.md), (5) quick local WebUI demo setup with [Gradio](#chat-with-our-demo-on-gradio), and (6) online web demo on [server](https://minicpm-omni-webdemo-us.modelbest.cn/).
|
| 51 |
|
| 52 |
|
|
|
|
| 53 |
**Model Architecture.**
|
| 54 |
|
| 55 |
- **End-to-end Omni-modal Architecture.** Different modality encoder/decoders are connected and trained in an **end-to-end** fashion to fully exploit rich multimodal knowledge.
|
|
|
|
| 27 |
[GitHub](https://github.com/OpenBMB/MiniCPM-o) | [Online Demo](https://minicpm-omni-webdemo-us.modelbest.cn)</a>
|
| 28 |
|
| 29 |
|
| 30 |
+
### News
|
| 31 |
+
|
| 32 |
+
* [2025.01.16] ⭐️⭐️⭐️ MiniCPM-o tops GitHub Trending and reaches top-3 on Hugging Face Trending!
|
| 33 |
+
|
| 34 |
## MiniCPM-o 2.6
|
| 35 |
|
| 36 |
+
|
| 37 |
**MiniCPM-o 2.6** is the latest and most capable model in the MiniCPM-o series. The model is built in an end-to-end fashion based on SigLip-400M, Whisper-medium-300M, ChatTTS-200M, and Qwen2.5-7B with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-V 2.6, and introduces new features for real-time speech conversation and multimodal live streaming. Notable features of MiniCPM-o 2.6 include:
|
| 38 |
|
| 39 |
- 🔥 **Leading Visual Capability.**
|
|
|
|
| 55 |
MiniCPM-o 2.6 can be easily used in various ways: (1) [llama.cpp](https://github.com/OpenBMB/llama.cpp/blob/minicpm-omni/examples/llava/README-minicpmo2.6.md) support for efficient CPU inference on local devices, (2) [int4](https://huggingface.co/openbmb/MiniCPM-o-2_6-int4) and [GGUF](https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf) format quantized models in 16 sizes, (3) [vLLM](#efficient-inference-with-llamacpp-ollama-vllm) support for high-throughput and memory-efficient inference, (4) fine-tuning on new domains and tasks with [LLaMA-Factory](./docs/llamafactory_train.md), (5) quick local WebUI demo setup with [Gradio](#chat-with-our-demo-on-gradio), and (6) online web demo on [server](https://minicpm-omni-webdemo-us.modelbest.cn/).
|
| 56 |
|
| 57 |
|
| 58 |
+
|
| 59 |
**Model Architecture.**
|
| 60 |
|
| 61 |
- **End-to-end Omni-modal Architecture.** Different modality encoder/decoders are connected and trained in an **end-to-end** fashion to fully exploit rich multimodal knowledge.
|