update doc
This commit is contained in:
@@ -131,18 +131,6 @@ aha run -m Qwen/Qwen3-ASR-0.6B -i "audio.wav"
|
|||||||
# Run local all-MiniLM-L6-v2 embedding (native safetensors)
|
# Run local all-MiniLM-L6-v2 embedding (native safetensors)
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
|
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
|
||||||
|
|
||||||
# Run local all-MiniLM-L6-v2 embedding (GGUF)
|
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format gguf --gguf-path D:\model_download\All-MiniLM-L6-v2-Embedding-GGUF --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
|
|
||||||
|
|
||||||
# Run local all-MiniLM-L6-v2 embedding (ONNX)
|
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format onnx --onnx-path D:\model_download\all-MiniLM-L6-v2\onnx --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
|
|
||||||
|
|
||||||
# Run local GLM-OCR (GGUF)
|
|
||||||
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format gguf --gguf-path D:\model_download\GLM-OCR-GGUF
|
|
||||||
|
|
||||||
# Run local GLM-OCR (ONNX)
|
|
||||||
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format onnx --onnx-path D:\model_download\GLM-OCR-ONNX --tokenizer-dir D:\model_download\GLM-OCR-ONNX
|
|
||||||
|
|
||||||
# Start service only (model already downloaded)
|
# Start service only (model already downloaded)
|
||||||
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
|
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
|
||||||
|
|
||||||
|
|||||||
@@ -130,18 +130,6 @@ aha run -m Qwen/Qwen3-ASR-0.6B -i "audio.wav"
|
|||||||
# 本地运行 all-MiniLM-L6-v2 向量模型(原生 safetensors)
|
# 本地运行 all-MiniLM-L6-v2 向量模型(原生 safetensors)
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
|
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --weight-path D:\model_download\all-MiniLM-L6-v2
|
||||||
|
|
||||||
# 本地运行 all-MiniLM-L6-v2 向量模型(GGUF)
|
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format gguf --gguf-path D:\model_download\All-MiniLM-L6-v2-Embedding-GGUF --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
|
|
||||||
|
|
||||||
# 本地运行 all-MiniLM-L6-v2 向量模型(ONNX)
|
|
||||||
aha run -m all-minilm-l6-v2 -i "Rust embedding test" --artifact-format onnx --onnx-path D:\model_download\all-MiniLM-L6-v2\onnx --tokenizer-dir D:\model_download\all-MiniLM-L6-v2
|
|
||||||
|
|
||||||
# 本地运行 GLM-OCR(GGUF)
|
|
||||||
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format gguf --gguf-path D:\model_download\GLM-OCR-GGUF
|
|
||||||
|
|
||||||
# 本地运行 GLM-OCR(ONNX)
|
|
||||||
aha run -m glm-ocr -i .\assets\img\ocr_test1.png --artifact-format onnx --onnx-path D:\model_download\GLM-OCR-ONNX --tokenizer-dir D:\model_download\GLM-OCR-ONNX
|
|
||||||
|
|
||||||
# 仅启动服务(模型已下载)
|
# 仅启动服务(模型已下载)
|
||||||
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
|
aha serv -m Qwen/Qwen3-ASR-0.6B -p 10100
|
||||||
|
|
||||||
|
|||||||
@@ -118,9 +118,6 @@ aha run -m FunAudioLLM/Fun-ASR-Nano-2512 -i "语音转写:" -i "audio.wav" --w
|
|||||||
# qwen3 text generation (single input)
|
# qwen3 text generation (single input)
|
||||||
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
|
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
|
||||||
|
|
||||||
# qwen3 GGUF text generation (single input)
|
|
||||||
aha run -m qwen3-0.6b -i "hello" --artifact-format gguf --gguf-path /path/to/Qwen3-0.6B-Q8_0.gguf
|
|
||||||
|
|
||||||
# qwen2.5vl image understanding (two inputs: prompt text + image file)
|
# qwen2.5vl image understanding (two inputs: prompt text + image file)
|
||||||
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
|
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
|
||||||
|
|
||||||
|
|||||||
+1
-5
@@ -118,9 +118,6 @@ aha run -m FunAudioLLM/Fun-ASR-Nano-2512 -i "语音转写:" -i "audio.wav" --w
|
|||||||
# qwen3 文本生成(单个输入)
|
# qwen3 文本生成(单个输入)
|
||||||
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
|
aha run -m Qwen/Qwen3-0.6B -i "你好" --weight-path /path/to/model
|
||||||
|
|
||||||
# qwen3 GGUF 文本生成(单个输入)
|
|
||||||
aha run -m qwen3-0.6b -i "你好" --artifact-format gguf --gguf-path /path/to/Qwen3-0.6B-Q8_0.gguf
|
|
||||||
|
|
||||||
# qwen2.5vl 图像理解(两个输入:提示文本 + 图片文件)
|
# qwen2.5vl 图像理解(两个输入:提示文本 + 图片文件)
|
||||||
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
|
aha run -m Qwen/Qwen2.5-VL-3B-Instruct -i "请分析图片并提取所有可见文本内容,按从左到右、从上到下的布局,返回纯文本" -i "image.jpg" --weight-path /path/to/model
|
||||||
|
|
||||||
@@ -145,8 +142,7 @@ GGUF/ONNX模型必须指定本地文件路径
|
|||||||
**语法:**
|
**语法:**
|
||||||
```bash
|
```bash
|
||||||
aha serv [OPTIONS] --model <MODEL> [--weight-path <WEIGHT_PATH>] [--gguf-path <GGUF_PATH>] \
|
aha serv [OPTIONS] --model <MODEL> [--weight-path <WEIGHT_PATH>] [--gguf-path <GGUF_PATH>] \
|
||||||
[--mmproj-path <MMPROJ_PATH>] [--onnx-path <ONNX_PATH>] [--tokenizer-dir <TOKENIZER_DIR>] \
|
[--mmproj-path <MMPROJ_PATH>] [--onnx-path <ONNX_PATH>] [--config-path <CONFIG_PATH>]
|
||||||
[--artifact-format <ARTIFACT_FORMAT>]
|
|
||||||
```
|
```
|
||||||
|
|
||||||
**选项:**
|
**选项:**
|
||||||
|
|||||||
Reference in New Issue
Block a user