From 46ee721d7413a5e9756c6635791b7d768988d11a Mon Sep 17 00:00:00 2001 From: jhqxxx <18280426169@163.com> Date: Mon, 6 Apr 2026 19:32:25 +0800 Subject: [PATCH] update doc --- Cargo.lock | 2 +- Cargo.toml | 4 +- README.md | 6 ++ README.zh-CN.md | 5 ++ docs/api.md | 142 ++++++++++++++++++++++++++++++++ docs/api.zh-CN.md | 145 ++++++++++++++++++++++++++++++++- docs/changelog.md | 3 + docs/changelog.zh-CN.md | 3 + docs/cli.md | 27 +----- docs/cli.zh-CN.md | 24 ------ docs/supported-models.md | 80 ++++-------------- docs/supported-models.zh-CN.md | 79 ++++-------------- src/lib.rs | 2 + 13 files changed, 339 insertions(+), 183 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 1003d19..83aaf7c 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -21,7 +21,7 @@ dependencies = [ [[package]] name = "aha" -version = "0.2.4" +version = "0.2.5" dependencies = [ "ahash", "anyhow", diff --git a/Cargo.toml b/Cargo.toml index cd414fa..9556c7a 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,10 +1,10 @@ [package] name = "aha" -version = "0.2.4" +version = "0.2.5" edition = "2024" repository = "https://github.com/jhqxxx/aha" license = "Apache-2.0" -description = "aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR), MiniCPM4, VoxCPM/1.5, DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5/2VL/2.5VL)" +description = "aha model inference library, now supports Qwen(2.5VL/3/3VL/3.5/ASR/3Embedding/3Reranker), MiniCPM4, VoxCPM/1.5, DeepSeek-OCR/2, Hunyuan-OCR, PaddleOCR-VL/1.5, RMBG2.0, GLM(ASR-Nano-2512/OCR), Fun-ASR-Nano-2512, LFM(2/2.5/2VL/2.5VL)" [dependencies] candle-core = { version = "0.9.2" } diff --git a/README.md b/README.md index 3b4d4fa..eca7f6f 100644 --- a/README.md +++ b/README.md @@ -35,6 +35,9 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR | | **TTS** | VoxCPM, VoxCPM1.5 | | **Image** | RMBG-2.0 (background removal) | +| **Embedding** | Qwen3-Embedding, all-MiniLM-L6-v2 | +| **Reranker** | Qwen3-Reranker | + ## Why aha? - **🚀 High-Performance Inference** - Powered by Candle framework for efficient tensor computation and model inference @@ -46,6 +49,9 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an - **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing ## Changelog +### 0.2.5 (2026-04-06) +- add qwen3-embedding/qwen3-reranker/all-minilm-l6-v2 + ### 2026-04-03 - CLI update: subcommand must be specified - ChatCompletionParameters add repeat_penalty and repeat_last_n diff --git a/README.zh-CN.md b/README.zh-CN.md index 85acc65..fa9a44c 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -34,6 +34,8 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理 | **ASR** | GLM-ASR-Nano, Fun-ASR-Nano, Qwen3-ASR | | **TTS** | VoxCPM, VoxCPM1.5 | | **图像** | RMBG-2.0 (背景移除) | +| **嵌入** | Qwen3-Embedding, all-MiniLM-L6-v2 | +| **重排序** | Qwen3-Reranker | ## 为什么选择 aha？ - **🚀 高性能推理** - 基于 Candle 框架，提供高效的张量计算和模型推理 @@ -46,6 +48,9 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理 ## 更新日志 ## Changelog +### 0.2.5 (2026-04-06) +- 添加 qwen3-embedding/qwen3-reranker/all-minilm-l6-v2 + ### 2026-04-03 - CLI 更新: 必须指定子命令 - ChatCompletionParameters 新增 repeat_penalty 和 repeat_last_n 参数 diff --git a/docs/api.md b/docs/api.md index 4cda44d..c69f670 100644 --- a/docs/api.md +++ b/docs/api.md @@ -541,6 +541,148 @@ curl http://127.0.0.1:10100/images/remove_background \ Returns the processed image in base64 PNG format. +### Embeddings +Generate text embeddings. + +#### Endpoints +``` +POST /embeddings +POST /v1/embeddings +``` + +#### Request Body +| Parameter | Type | Required | Description | +|------|------|------|------| +| `model` | string | No | Model identifier (optional, ignored - uses loaded model) | +| `input` | string or array | Yes | Text or array of texts to embed | + +#### Examples +Single text： +```bash +curl http://127.0.0.1:10100/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "input": "Hello world" + }' +``` + +Multiple texts： +```bash +curl http://127.0.0.1:10100/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "input": ["Hello world", "How are you?", "Goodbye"] + }' +``` + +#### Response +**Success (HTTP 200):** +```json +{ + "object": "list", + "data": [ + { + "object": "embedding", + "index": 0, + "embedding": [0.1, 0.2, 0.3, ...] + } + ], + "model": "model-name" +} +``` + +**Error (HTTP 400):** +```json +{ + "error": "embedding input must be a string or an array of strings" +} +``` + +### Rerank +Re-rank a list of documents according to a query. + +#### Endpoint +``` +POST /rerank +POST /v1/rerank +``` + +#### Request Body +| Parameter | Type | Required | Description | +|------|------|------|------| +| `model` | string | No | 模型标识符 | +| `query` | string | Yes | Query text | +| `documents` | array | Yes | Array of document texts to re-rank | +| `top_n` | int | No | Return top N results (optional) | + +#### Example +Basic re-ranking： +```bash +curl http://127.0.0.1:10100/rerank \ + -H "Content-Type: application/json" \ + -d '{ + "query": "artificial intelligence", + "documents": [ + "Machine learning is a form of artificial intelligence", + "Apple is a fruit", + "Deep learning belongs to the field of artificial intelligence" + ] + }' +``` + +Limit return count： +```bash +curl http://127.0.0.1:10100/rerank \ + -H "Content-Type: application/json" \ + -d '{ + "query": "artificial intelligence", + "documents": [ + "Machine learning is a form of artificial intelligence", + "Apple is a fruit", + "Deep learning belongs to the field of artificial intelligence" + ], + "top_n": 2 + }' +``` + +#### Response +**Success (HTTP 200):** +```json +{ + "object": "list", + "model": "model-name", + "results": [ + { + "index": 0, + "relevance_score": 0.95, + "document": "Machine learning is a form of artificial intelligence" + }, + { + "index": 2, + "relevance_score": 0.87, + "document": "Deep learning belongs to the field of artificial intelligence" + } + ] +} +``` + +**Error (HTTP 400):** +```json +{ + "error": "rerank query cannot be empty" +} +``` + +#### Parameter Description +| Parameter | Type | Description | +|------|------|-----| +| `model` | string | Model identifier | +| `object` | string | Fixed value: "list" | +| `results` | array | Re-ranked results array | +| `index` | int | Original document index | +| `relevance_score` | f32 | Relevance score (higher is more relevant) | +| `document` | string | Original document text | + ### Graceful Shutdown Gracefully shut down the AHA server. This endpoint initiates a graceful shutdown process that: diff --git a/docs/api.zh-CN.md b/docs/api.zh-CN.md index 1270242..2f4933c 100644 --- a/docs/api.zh-CN.md +++ b/docs/api.zh-CN.md @@ -149,8 +149,10 @@ curl http://127.0.0.1:10100/models #### 端点 ``` -POST /chat/completions +POST /chat/completions +POST /v1/chat/completions ``` +两个端点使用相同的处理函数并返回相同的响应。`/v1/chat/completions` 路径遵循 OpenAI 的标准 API 约定。 #### 请求体 @@ -544,6 +546,147 @@ curl http://127.0.0.1:10100/images/remove_background \ 以base64 PNG 格式返回处理后的图像。 +### 嵌入 +生成文本嵌入向量。 + +#### 端点 +``` +POST /embeddings +POST /v1/embeddings +``` + +#### 请求体 +| 参数 | 类型 | 必需 | 描述 | +|------|------|------|------| +| `model` | string | 否 | 模型标识符 | +| `input` | string 或 array | 是 | 要嵌入的文本或文本数组 | + +#### 示例 +单个文本： +```bash +curl http://127.0.0.1:10100/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "input": "Hello world" + }' +``` + +多个文本： +```bash +curl http://127.0.0.1:10100/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "input": ["Hello world", "How are you?", "Goodbye"] + }' +``` + +#### 响应 +**成功 (HTTP 200):** +```json +{ + "object": "list", + "data": [ + { + "object": "embedding", + "index": 0, + "embedding": [0.1, 0.2, 0.3, ...] + } + ], + "model": "model-name" +} +``` + +**错误 (HTTP 400):** +```json +{ + "error": "embedding input must be a string or an array of strings" +} +``` + +### 重排 +对文档列表根据查询进行重新排序。 + +#### 端点 +``` +POST /rerank +POST /v1/rerank +``` + +#### 请求体 +| 参数 | 类型 | 必需 | 描述 | +|------|------|------|------| +| `model` | string | 否 | 模型标识符 | +| `query` | string | 是 | 查询文本 | +| `documents` | array | 是 | 要重排序的文档文本数组 | +| `top_n` | int | 否 | 返回前N个结果（可选） | + +#### 示例 +基础重排序： +```bash +curl http://127.0.0.1:10100/rerank \ + -H "Content-Type: application/json" \ + -d '{ + "query": "人工智能", + "documents": [ + "机器学习是一种人工智能技术", + "苹果是一种水果", + "深度学习属于人工智能领域" + ] + }' +``` + +限制返回数量： +```bash +curl http://127.0.0.1:10100/rerank \ + -H "Content-Type: application/json" \ + -d '{ + "query": "人工智能", + "documents": [ + "机器学习是一种人工智能技术", + "苹果是一种水果", + "深度学习属于人工智能领域" + ], + "top_n": 2 + }' +``` + +#### 响应 +**成功 (HTTP 200):** +```json +{ + "object": "list", + "model": "model-name", + "results": [ + { + "index": 0, + "relevance_score": 0.95, + "document": "机器学习是一种人工智能技术" + }, + { + "index": 2, + "relevance_score": 0.87, + "document": "深度学习属于人工智能领域" + } + ] +} +``` + +**错误 (HTTP 400):** +```json +{ + "error": "rerank query cannot be empty" +} +``` + +#### 字段说明 +| 字段 | 类型 | 描述 | +|------|------|-----| +| `model` | string | 模型标识符 | +| `object` | string | 固定值："list" | +| `results` | array | 重排序结果数组 | +| `index` | int | 原始文档索引 | +| `relevance_score` | f32 | 相关性分数（越高越相关） | +| `document` | string | 原始文档文本 | ### 优雅关机 diff --git a/docs/changelog.md b/docs/changelog.md index b7e63e6..0cec893 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -5,6 +5,9 @@ All notable changes to aha will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +### 0.2.5 (2026-04-06) +- add qwen3-embedding/qwen3-reranker/all-minilm-l6-v2 + ### 2026-04-03 - CLI update: subcommand must be specified - ChatCompletionParameters add repeat_penalty and repeat_last_n diff --git a/docs/changelog.zh-CN.md b/docs/changelog.zh-CN.md index e695352..c034a1f 100644 --- a/docs/changelog.zh-CN.md +++ b/docs/changelog.zh-CN.md @@ -5,6 +5,9 @@ 格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/)， 本项目遵循 [语义化版本](https://semver.org/lang/zh-CN/spec/v2.0.0.html)。 +### 0.2.5 (2026-04-06) +- 添加 qwen3-embedding/qwen3-reranker/all-minilm-l6-v2 + ### 2026-04-03 - CLI 更新: 必须指定子命令 - ChatCompletionParameters 新增 repeat_penalty 和 repeat_last_n 参数 diff --git a/docs/cli.md b/docs/cli.md index f0de349..9d36a48 100644 --- a/docs/cli.md +++ b/docs/cli.md @@ -67,10 +67,6 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct --weight-path /path/to/model # use gguf-path and mmproj-path aha cli -m qwen3.5-gguf --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf -# run service with ONNX artifact -aha cli -m qwen3-embedding-0.6b --artifact-format onnx \ - --onnx-path /path/to/Qwen3-Embedding-0.6B-ONNX \ - --tokenizer-dir /path/to/Qwen3-Embedding-0.6B-ONNX ``` ### run - Direct model inference @@ -138,10 +134,6 @@ aha run -m qwen3.5-gguf -i 你如何看待AI --gguf-path /path/to/xxx.gguf aha run -m qwen3.5-gguf -i 提取图片中的文本 -i https://ai.bdstatic.com/file/C56CC9B274CF460CA33 63E59ECD94423 --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf -# Qwen3.5 ONNX text-only generation -aha run -m qwen3.5-0.8b -i "hello" --artifact-format onnx \ - --onnx-path /path/to/Qwen3.5-0.8B-ONNX \ - --tokenizer-dir /path/to/Qwen3.5-0.8B-ONNX ``` @@ -168,8 +160,7 @@ aha serv [OPTIONS] --model [--weight-path ] [--gguf-path ` | Local GGUF model weight path（required when using GGUF models） | - | | `--mmproj-path ` | Local mmproj GGUF weight path（optional，If not specified, the module will not be loaded） | - | | `--onnx-path ` | Local ONNX model directory/file path（required when using ONNX models） | - | -| `--tokenizer-dir ` | Tokenizer/config directory for GGUF/ONNX | - | -| `--artifact-format ` | Artifact format (`auto|safetensors|gguf|onnx`) | auto | +| `--config-path ` | extra config path for gguf/onnx | - | **Examples:** @@ -432,22 +423,6 @@ After the service starts, the following API endpoints are available: - **Format**: JSON response -## Notes - -1. **Local-path rule for GGUF/ONNX**: GGUF and ONNX artifacts are local-path only; use `--gguf-path` or `--onnx-path`. Remote download management is only for safetensors models. - -2. **Artifact selection**: `--artifact-format auto` uses model default; you can force `safetensors|gguf|onnx` explicitly. - -3. **Tokenizer directory**: For GGUF/ONNX, if tokenizer files are not colocated with model files, set `--tokenizer-dir`. - -4. **Download retry mechanism**: By default, retries 3 times, waiting 2 seconds after each failure before retrying. You can adjust the retry count with `--download-retries`. - -5. **Default save directory**: Models are saved to `~/.aha/` directory by default, which can be customized via `--save-dir` or `-s` parameter. - -6. **Port occupation**: Ensure the specified port is not occupied before starting the service. The default port is 10100. - -7. **Permission issues**: If saving to a system directory (such as `/data/models`), ensure you have the corresponding write permissions. - ## Getting Help ```bash diff --git a/docs/cli.zh-CN.md b/docs/cli.zh-CN.md index 938058d..f0a92c8 100644 --- a/docs/cli.zh-CN.md +++ b/docs/cli.zh-CN.md @@ -67,10 +67,6 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct --weight-path /path/to/model # 指定gguf-path和mmproj-path aha cli -m qwen3.5-gguf --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf -# 使用 ONNX 模型启动服务 -aha cli -m qwen3-embedding-0.6b --artifact-format onnx \ - --onnx-path /path/to/Qwen3-Embedding-0.6B-ONNX \ - --tokenizer-dir /path/to/Qwen3-Embedding-0.6B-ONNX ``` ### run - 直接模型推理 @@ -138,10 +134,6 @@ aha run -m qwen3.5-gguf -i 你如何看待AI --gguf-path /path/to/xxx.gguf aha run -m qwen3.5-gguf -i 提取图片中的文本 -i https://ai.bdstatic.com/file/C56CC9B274CF460CA33 63E59ECD94423 --gguf-path /path/to/xxx.gguf --mmproj-path /path/to/mmproj-xxx.gguf -# Qwen3.5 ONNX 文本生成（text-only） -aha run -m qwen3.5-0.8b -i "你好" --artifact-format onnx \ - --onnx-path /path/to/Qwen3.5-0.8B-ONNX \ - --tokenizer-dir /path/to/Qwen3.5-0.8B-ONNX ``` ### serv - 启动服务 @@ -432,22 +424,6 @@ aha cli -m Qwen/Qwen3-VL-2B-Instruct -a 0.0.0.0 -p 8080 - **格式**: JSON 响应 -## 注意事项 - -1. **GGUF/ONNX 仅支持本地路径**：请使用 `--gguf-path` 或 `--onnx-path`。自动下载管理仅适用于 safetensors 模型。 - -2. **制品格式选择**：`--artifact-format auto` 使用模型默认格式，也可显式指定 `safetensors|gguf|onnx`。 - -3. **tokenizer 目录**：GGUF/ONNX 若未与 tokenizer/config 同目录，请额外指定 `--tokenizer-dir`。 - -4. **下载重试机制**：默认重试 3 次，每次失败后等待 2 秒再重试。可通过 `--download-retries` 调整重试次数。 - -5. **默认保存目录**：模型默认保存到 `~/.aha/` 目录下，可通过 `--save-dir` 或 `-s` 参数自定义。 - -6. **端口占用**：启动服务前确保指定的端口未被占用，默认端口为 10100。 - -7. **权限问题**：如果保存到系统目录（如 `/data/models`），确保有相应的写入权限。 - ## 获取帮助 ```bash diff --git a/docs/supported-models.md b/docs/supported-models.md index e1bafba..28b26c2 100644 --- a/docs/supported-models.md +++ b/docs/supported-models.md @@ -7,6 +7,7 @@ Available models: Model ID Owner type Download -------------------------------------------------------------------------------- +sentence-transformers/all-MiniLM-L6-v2 sentence-transformers embedding ✔ LiquidAI/LFM2-1.2B LiquidAI llm ✔ LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔ LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔ @@ -14,9 +15,9 @@ LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔ OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔ Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔ Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm -Qwen/Qwen3-0.6B Qwen llm ✔ -Qwen/Qwen3-1.7B Qwen llm -Qwen/Qwen3-4B Qwen llm +Qwen/Qwen3-0.6B Qwen llm ✔ +Qwen/Qwen3-1.7B Qwen llm ✔ +Qwen/Qwen3-4B Qwen llm ✔ Qwen/Qwen3.5-0.8B Qwen vlm ✔ Qwen/Qwen3.5-2B Qwen vlm Qwen/Qwen3.5-4B Qwen vlm @@ -24,6 +25,12 @@ Qwen/Qwen3.5-9B Qwen vlm qwen3.5-gguf none vlm Qwen/Qwen3-ASR-0.6B Qwen asr ✔ Qwen/Qwen3-ASR-1.7B Qwen asr +Qwen/Qwen3-Embedding-0.6B Qwen embedding ✔ +Qwen/Qwen3-Embedding-4B Qwen embedding +Qwen/Qwen3-Embedding-8B Qwen embedding +Qwen/Qwen3-Reranker-0.6B Qwen reranker ✔ +Qwen/Qwen3-Reranker-4B Qwen reranker +Qwen/Qwen3-Reranker-8B Qwen reranker Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔ Qwen/Qwen3-VL-4B-Instruct Qwen vlm Qwen/Qwen3-VL-8B-Instruct Qwen vlm @@ -53,20 +60,16 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔ ## Embedding -| Model | Parameters | Description | License | +| Model | Parameters | Model Id | License | |-------|-----------|-------------|---------| -| **Qwen3-Embedding-0.6B** | 0.6B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Embedding-4B** | 4B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Embedding-8B** | 8B | Text embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **all-MiniLM-L6-v2** | 22M | Sentence-transformers embedding (safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) | +| **Qwen3-Embedding** | 0.6B
4B
8B| Qwen/Qwen3-Embedding-0.6B
Qwen/Qwen3-Embedding-4B
Qwen/Qwen3-Embedding-8B | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | +| **all-MiniLM-L6-v2** | 91M | sentence-transformers/all-MiniLM-L6-v2 | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) | ## Reranker -| Model | Parameters | Description | License | +| Model | Parameters | Model Id | License | |-------|-----------|-------------|---------| -| **Qwen3-Reranker-0.6B** | 0.6B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Reranker-4B** | 4B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Reranker-8B** | 8B | Text reranking (embedding-similarity baseline, safetensors / gguf / onnx) | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | +| **Qwen3-Reranker** | 0.6B
4B
8B| Qwen/Qwen3-Reranker-0.6B
Qwen/Qwen3-Reranker-4B
Qwen/Qwen3-Reranker-8B | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | ## Vision & Multimodal @@ -88,8 +91,6 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔ | **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | -GLM-OCR local artifacts: `safetensors`, `gguf`, `onnx` - ## Speech Recognition (ASR) | Model | Parameters | Language | Model Id | License | @@ -117,57 +118,6 @@ Models are sourced from: - [Hugging Face](https://huggingface.co) - Primary model hub - [ModelScope](https://modelscope.cn) - Chinese model hub -## Registered Repositories (Not Runtime-Integrated Yet) - -The following repositories are now cataloged for future integration, but are **not** directly runnable in current `aha` runtime yet: - -### MLX / Format-Specific Variants -- Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit - -### Embedding Models -- google/embeddinggemma-300m -- ggml-org/embeddinggemma-300M-GGUF -- onnx-community/embeddinggemma-300m-ONNX -- unsloth/embeddinggemma-300m-GGUF -- onnx-community/Qwen3-Embedding-0.6B-ONNX -- Qwen/Qwen3-Embedding-0.6B-GGUF -- onnx-community/Qwen3-Embedding-4B-ONNX -- Qwen/Qwen3-Embedding-4B-GGUF -- Qwen/Qwen3-Embedding-8B-GGUF -- onnx-community/Qwen3-Embedding-8B-ONNX -- perplexity-ai/pplx-embed-v1-0.6b -- nomic-ai/nomic-embed-text-v2-moe -- nomic-ai/nomic-embed-text-v2-moe-GGUF -- jinaai/jina-embeddings-v5-text-small -- jinaai/jina-embeddings-v5-text-nano -- jinaai/jina-embeddings-v5-text-small-text-matching -- jinaai/jina-embeddings-v5-text-small-text-matching-GGUF -- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 - -### Reranker Models -- BAAI/bge-reranker-v2-m3 -- ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF - -### ONNX Repositories -- onnx-community/GLM-OCR-ONNX -- onnx-community/Qwen3-Reranker-0.6B-ONNX -- onnx-community/Qwen3.5-2B-ONNX -- onnx-community/Qwen3.5-4B-ONNX -- onnx-community/Qwen3.5-0.8B-ONNX -- onnx-community/Qwen3-VL-2B-Instruct-ONNX -- onnx-community/ONNX_Qwen3-Embedding-0.6B -- onnx-community/Nanbeige4.1-3B-ONNX -- onnx-community/Qwen3-Embedding-8B-ONNX -- onnx-community/Qwen3-Embedding-4B-ONNX -- onnx-community/bge-reranker-v2-m3-ONNX -- onnx-community/all-MiniLM-L6-v2-ONNX - ## Adding New Models See [Development Guide](./development.md) for instructions on adding new model integrations. diff --git a/docs/supported-models.zh-CN.md b/docs/supported-models.zh-CN.md index f574d06..416f580 100644 --- a/docs/supported-models.zh-CN.md +++ b/docs/supported-models.zh-CN.md @@ -7,6 +7,7 @@ Available models: Model ID Owner type Download -------------------------------------------------------------------------------- +sentence-transformers/all-MiniLM-L6-v2 sentence-transformers embedding ✔ LiquidAI/LFM2-1.2B LiquidAI llm ✔ LiquidAI/LFM2.5-1.2B-Instruct LiquidAI llm ✔ LiquidAI/LFM2.5-VL-1.6B LiquidAI vlm ✔ @@ -14,9 +15,9 @@ LiquidAI/LFM2-VL-1.6B LiquidAI vlm ✔ OpenBMB/MiniCPM4-0.5B OpenBMB llm ✔ Qwen/Qwen2.5-VL-3B-Instruct Qwen vlm ✔ Qwen/Qwen2.5-VL-7B-Instruct Qwen vlm -Qwen/Qwen3-0.6B Qwen llm ✔ -Qwen/Qwen3-1.7B Qwen llm -Qwen/Qwen3-4B Qwen llm +Qwen/Qwen3-0.6B Qwen llm ✔ +Qwen/Qwen3-1.7B Qwen llm ✔ +Qwen/Qwen3-4B Qwen llm ✔ Qwen/Qwen3.5-0.8B Qwen vlm ✔ Qwen/Qwen3.5-2B Qwen vlm Qwen/Qwen3.5-4B Qwen vlm @@ -24,6 +25,12 @@ Qwen/Qwen3.5-9B Qwen vlm qwen3.5-gguf none vlm Qwen/Qwen3-ASR-0.6B Qwen asr ✔ Qwen/Qwen3-ASR-1.7B Qwen asr +Qwen/Qwen3-Embedding-0.6B Qwen embedding ✔ +Qwen/Qwen3-Embedding-4B Qwen embedding +Qwen/Qwen3-Embedding-8B Qwen embedding +Qwen/Qwen3-Reranker-0.6B Qwen reranker ✔ +Qwen/Qwen3-Reranker-4B Qwen reranker +Qwen/Qwen3-Reranker-8B Qwen reranker Qwen/Qwen3-VL-2B-Instruct Qwen vlm ✔ Qwen/Qwen3-VL-4B-Instruct Qwen vlm Qwen/Qwen3-VL-8B-Instruct Qwen vlm @@ -52,20 +59,16 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔ ## Embedding -| 模型 | 参数量 | 描述 | 开源协议 | +| 模型 | 参数量 | 模型id | 开源协议 | |------|--------|------|---------| -| **Qwen3-Embedding-0.6B** | 0.6B | 文本向量（safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Embedding-4B** | 4B | 文本向量（safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Embedding-8B** | 8B | 文本向量（safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **all-MiniLM-L6-v2** | 22M | sentence-transformers 文本向量（safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) | +| **Qwen3-Embedding** | 0.6B
4B
8B| Qwen/Qwen3-Embedding-0.6B
Qwen/Qwen3-Embedding-4B
Qwen/Qwen3-Embedding-8B | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | +| **all-MiniLM-L6-v2** | 91M | sentence-transformers/all-MiniLM-L6-v2 | [Apache 2.0](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/LICENSE) | ## Reranker -| 模型 | 参数量 | 描述 | 开源协议 | +| 模型 | 参数量 | 模型id | 开源协议 | |------|--------|------|---------| -| **Qwen3-Reranker-0.6B** | 0.6B | 文本重排（embedding-similarity 基线，safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Reranker-4B** | 4B | 文本重排（embedding-similarity 基线，safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | -| **Qwen3-Reranker-8B** | 8B | 文本重排（embedding-similarity 基线，safetensors / gguf / onnx） | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | +| **Qwen3-Reranker** | 0.6B
4B
8B| Qwen/Qwen3-Reranker-0.6B
Qwen/Qwen3-Reranker-4B
Qwen/Qwen3-Reranker-8B | [Apache 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) | ## 视觉与多模态 @@ -86,7 +89,6 @@ ZhipuAI/GLM-OCR ZhipuAI ocr ✔ | **DeepSeek-OCR** | 多语言 | deepseek-ai/DeepSeek-OCR
deepseek-ai/DeepSeek-OCR-2 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | | **GLM-OCR** | 8 | ZhipuAI/GLM-OCR | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | -GLM-OCR 本地制品格式：`safetensors`、`gguf`、`onnx` ## 语音识别 (ASR) @@ -116,57 +118,6 @@ GLM-OCR 本地制品格式：`safetensors`、`gguf`、`onnx` - [Hugging Face](https://huggingface.co) - 主模型中心 - [ModelScope](https://modelscope.cn) - 中文模型中心 -## 已收录仓库（当前运行时暂未直接接入） - -以下仓库已纳入项目模型目录，但当前 `aha` 运行时尚不能直接推理： - -### MLX / 特定格式变体 -- Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit -- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-6bit -- Jackrong/MLX-Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-8bit - -### Embedding 模型 -- google/embeddinggemma-300m -- ggml-org/embeddinggemma-300M-GGUF -- onnx-community/embeddinggemma-300m-ONNX -- unsloth/embeddinggemma-300m-GGUF -- onnx-community/Qwen3-Embedding-0.6B-ONNX -- Qwen/Qwen3-Embedding-0.6B-GGUF -- onnx-community/Qwen3-Embedding-4B-ONNX -- Qwen/Qwen3-Embedding-4B-GGUF -- Qwen/Qwen3-Embedding-8B-GGUF -- onnx-community/Qwen3-Embedding-8B-ONNX -- perplexity-ai/pplx-embed-v1-0.6b -- nomic-ai/nomic-embed-text-v2-moe -- nomic-ai/nomic-embed-text-v2-moe-GGUF -- jinaai/jina-embeddings-v5-text-small -- jinaai/jina-embeddings-v5-text-nano -- jinaai/jina-embeddings-v5-text-small-text-matching -- jinaai/jina-embeddings-v5-text-small-text-matching-GGUF -- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 - -### Reranker 模型 -- BAAI/bge-reranker-v2-m3 -- ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF - -### ONNX 仓库 -- onnx-community/GLM-OCR-ONNX -- onnx-community/Qwen3-Reranker-0.6B-ONNX -- onnx-community/Qwen3.5-2B-ONNX -- onnx-community/Qwen3.5-4B-ONNX -- onnx-community/Qwen3.5-0.8B-ONNX -- onnx-community/Qwen3-VL-2B-Instruct-ONNX -- onnx-community/ONNX_Qwen3-Embedding-0.6B -- onnx-community/Nanbeige4.1-3B-ONNX -- onnx-community/Qwen3-Embedding-8B-ONNX -- onnx-community/Qwen3-Embedding-4B-ONNX -- onnx-community/bge-reranker-v2-m3-ONNX -- onnx-community/all-MiniLM-L6-v2-ONNX - ## 添加新模型 参见 [开发指南](./development.zh-CN.md) 了解添加新模型集成的说明。 diff --git a/src/lib.rs b/src/lib.rs index 4626a8e..9cd29fb 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -5,3 +5,5 @@ pub mod params; pub mod position_embed; pub mod tokenizer; pub mod utils; + +pub use candle_core::Device;