Helpme
#30
by
HamBoneTheSniff
- opened
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
- en
|
5 |
- zh
|
6 |
datasets:
|
7 |
-
-
|
8 |
---
|
9 |
|
10 |
|
@@ -17,7 +17,7 @@ datasets:
|
|
17 |
|
18 |
#### π Pinned
|
19 |
|
20 |
-
* [2024.05.28] πππ MiniCPM-Llama3-V 2.5 now fully supports its
|
21 |
* [2024.05.28] π« We now support LoRA fine-tuning for MiniCPM-Llama3-V 2.5, using only 2 V100 GPUs! See more statistics [here](https://github.com/OpenBMB/MiniCPM-V/tree/main/finetune#model-fine-tuning-memory-usage-statistics).
|
22 |
* [2024.05.23] π 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 ππππ. Click [here](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/compare_with_phi-3_vision.md) to view more details.
|
23 |
* [2024.05.23] π₯π₯π₯ MiniCPM-V tops GitHub Trending and HuggingFace Trending! Our demo, recommended by Hugging Face Gradioβs official account, is available [here](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5). Come and try it out!
|
@@ -44,7 +44,7 @@ datasets:
|
|
44 |
Leveraging the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) method (the newest technology in the [RLHF-V](https://github.com/RLHF-V) [CVPR'24] series), MiniCPM-Llama3-V 2.5 exhibits more trustworthy behavior. It achieves **10.3%** hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%), achieving the best-level performance within the open-source community. [Data released](https://huggingface.co/datasets/openbmb/RLAIF-V-Dataset).
|
45 |
|
46 |
- π **Multilingual Support.**
|
47 |
-
Thanks to the strong multilingual capabilities of Llama 3 and the cross-lingual generalization technique from [VisCPM](https://github.com/OpenBMB/VisCPM), MiniCPM-Llama3-V 2.5 extends its bilingual (Chinese-English) multimodal capabilities to **over 30 languages including German, French, Spanish, Italian,
|
48 |
|
49 |
- π **Efficient Deployment.**
|
50 |
MiniCPM-Llama3-V 2.5 systematically employs **model quantization, CPU optimizations, NPU optimizations and compilation optimizations**, achieving high-efficiency deployment on edge devices. For mobile phones with Qualcomm chips, we have integrated the NPU acceleration framework QNN into llama.cpp for the first time. After systematic optimization, MiniCPM-Llama3-V 2.5 has realized a **150-fold acceleration in multimodal large model end-side image encoding** and a **3-fold increase in language decoding speed**.
|
|
|
4 |
- en
|
5 |
- zh
|
6 |
datasets:
|
7 |
+
- HaoyeZhang/RLAIF-V-Dataset
|
8 |
---
|
9 |
|
10 |
|
|
|
17 |
|
18 |
#### π Pinned
|
19 |
|
20 |
+
* [2024.05.28] πππ MiniCPM-Llama3-V 2.5 now fully supports its features in llama.cpp and ollama! Please pull the latest code **of our provided forks** ([llama.cpp](https://github.com/OpenBMB/llama.cpp/blob/minicpm-v2.5/examples/minicpmv/README.md), [ollama](https://github.com/OpenBMB/ollama/tree/minicpm-v2.5)). GGUF models in various sizes are available [here](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf/tree/main). We are working hard to merge PRs into official repositories. Please stay tuned! You can visit our [GitHub](https://github.com/OpenBMB/MiniCPM-V) repository for more information!
|
21 |
* [2024.05.28] π« We now support LoRA fine-tuning for MiniCPM-Llama3-V 2.5, using only 2 V100 GPUs! See more statistics [here](https://github.com/OpenBMB/MiniCPM-V/tree/main/finetune#model-fine-tuning-memory-usage-statistics).
|
22 |
* [2024.05.23] π 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 ππππ. Click [here](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/compare_with_phi-3_vision.md) to view more details.
|
23 |
* [2024.05.23] π₯π₯π₯ MiniCPM-V tops GitHub Trending and HuggingFace Trending! Our demo, recommended by Hugging Face Gradioβs official account, is available [here](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5). Come and try it out!
|
|
|
44 |
Leveraging the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) method (the newest technology in the [RLHF-V](https://github.com/RLHF-V) [CVPR'24] series), MiniCPM-Llama3-V 2.5 exhibits more trustworthy behavior. It achieves **10.3%** hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%), achieving the best-level performance within the open-source community. [Data released](https://huggingface.co/datasets/openbmb/RLAIF-V-Dataset).
|
45 |
|
46 |
- π **Multilingual Support.**
|
47 |
+
Thanks to the strong multilingual capabilities of Llama 3 and the cross-lingual generalization technique from [VisCPM](https://github.com/OpenBMB/VisCPM), MiniCPM-Llama3-V 2.5 extends its bilingual (Chinese-English) multimodal capabilities to **over 30 languages including German, French, Spanish, Italian, Russian etc.** [All Supported Languages](./assets/minicpm-llama-v-2-5_languages.md).
|
48 |
|
49 |
- π **Efficient Deployment.**
|
50 |
MiniCPM-Llama3-V 2.5 systematically employs **model quantization, CPU optimizations, NPU optimizations and compilation optimizations**, achieving high-efficiency deployment on edge devices. For mobile phones with Qualcomm chips, we have integrated the NPU acceleration framework QNN into llama.cpp for the first time. After systematic optimization, MiniCPM-Llama3-V 2.5 has realized a **150-fold acceleration in multimodal large model end-side image encoding** and a **3-fold increase in language decoding speed**.
|