diff --git a/README-en.md b/README-en.md index 00e0e0e..95f3e23 100644 --- a/README-en.md +++ b/README-en.md @@ -401,7 +401,7 @@ Solving [this issue](https://github.com/ollama/ollama/issues/2383) * After INT4 quantization, MiniCPM only occupies 2GB of space, meeting the requirements of inference on end devices. * We have made different adaptations for different operating systems. * **Note: The current open-source framework is still improving its support for mobile phones, and not all chips and operating system versions can successfully run MLC-LLM or LLMFarm.** -* Android, Harmony OS +* Android, HarmonyOS * Adapt based on open-source framework MLC-LLM. * Adapted for text model MiniCPM, and multimodel model MiniCPM-V. * Support MiniCPM-2B-SFT-INT4、MiniCPM-2B-DPO-INT4、MiniCPM-V. @@ -431,7 +431,7 @@ Solving [this issue](https://github.com/ollama/ollama/issues/2383) | Oneplus HD1905 | Android 10 | snapdragon 855 | 8 | 3.0 | | Oneplus HD1900 | Android 11 | snapdragon 855 | 8 | 3.0 | | Xiaomi MI 8 | Android 9 | snapdragon 845 | 6 | 2.3 | -| Huawei Nova 11SE | Harmony 4.0.0 | snapdragon 778 | 12 | 1.9 | +| Huawei Nova 11SE | HarmonyOS 4.0.0 | snapdragon 778 | 12 | 1.9 | | Xiaomi MIX 2 | Android 9 | snapdragon 835 | 6 | 1.3 | | iPhone 15 Pro | iOS 17.2.1 | A16 | 8 | 18.0 | | iPhone 15 | iOS 17.2.1 | A16 | 6 | 15.0 | diff --git a/README.md b/README.md index 80295a6..dd93f96 100644 --- a/README.md +++ b/README.md @@ -82,8 +82,8 @@ MiniCPM 是面壁智能与清华大学自然语言处理实验室共同开源的 注: 1. 模型训练为bf16训练,因此用bf16进行推理将取得最好的效果,其他的格式会由于精度问题造成一点的性能下降。 - 2. -llama-format后缀的模型是我们将MiniCPM结构的模型转化成了Llama结构的(主要将mup的参数化方案融合进了模型本身的参数)。使得Llama模型的使用者可以零成本尝试MiniCPM。[详见](#llamaformat) - 3. 感谢[贡献者](https://github.com/runfuture)对minicpm进行了[llama.cpp](https://github.com/ggerganov/llama.cpp)和[ollama](https://github.com/ollama/ollama)的适配 + 2. -llama-format后缀的模型是我们将MiniCPM结构的模型转化成了Llama结构的(主要将mup的参数化方案融合进了模型本身的参数)。使得Llama模型的使用者可以零成本尝试MiniCPM。[详见这里](#llamaformat) + 3. 感谢[@runfuture](https://github.com/runfuture)对MiniCPM进行了[llama.cpp](https://github.com/ggerganov/llama.cpp)和[ollama](https://github.com/ollama/ollama)的适配 * 多模态模型 @@ -130,7 +130,7 @@ print(responds)
##### MiniCPM-2B (Llama Format) -我们将minicpm的模型权重转化成了Llama代码可以直接调用的形式,以便大家尝试: +我们将MiniCPM的模型权重转化成了Llama代码可以直接调用的形式,以便大家尝试: ```python import torch from transformers import LlamaTokenizerFast, LlamaForCausalLM @@ -413,7 +413,7 @@ python inference.py --model_path