README.md

---
base_model: jiyi/hyact-qwen
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
该模型是基于Qwen2-7B训练的一个针对医学的大语言模型
⚠️注意训练的语料与精度过低，而且只是一个加了医疗问答的测试版本，尚不支持康复问答，后续会更具现有的语料进行医疗问答训练

# 我的目标：训练一个针对康复医学领域的全能模型
欢迎感兴趣的朋友一起分享数据集加速模型的训练
# jiyi/hyact-qwen-Q4_K_M-GGUF
This model was converted to GGUF format from [`jiyi/hyact-qwen`](https://huggingface.co/jiyi/hyact-qwen) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/jiyi/hyact-qwen) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo jiyi/hyact-qwen-Q4_K_M-GGUF --hf-file hyact-qwen-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo jiyi/hyact-qwen-Q4_K_M-GGUF --hf-file hyact-qwen-q4_k_m.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo jiyi/hyact-qwen-Q4_K_M-GGUF --hf-file hyact-qwen-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo jiyi/hyact-qwen-Q4_K_M-GGUF --hf-file hyact-qwen-q4_k_m.gguf -c 2048
```