duckkkk commited on
Commit
8cdcd78
路
verified 路
1 Parent(s): 253baf4

Model card

Browse files
Files changed (1) hide show
  1. README.md +50 -6
README.md CHANGED
@@ -1,26 +1,70 @@
1
  ---
2
  license: mit
3
  base_model: BAAI/bge-reranker-base
 
 
4
  tags:
5
  - dakera
 
 
 
 
 
 
 
6
  - mirror
7
  ---
8
 
9
- # bge-reranker-base
 
 
10
 
11
- An unmodified copy of the files [Dakera](https://dakera.ai) downloads for [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base), so Dakera installs keep working if an upstream repository moves or goes away. Dakera downloads from here first and falls back to the original repositories; both are checked against the same SHA-256.
12
 
13
- The model is by BAAI, released under the MIT licence. All credit goes to its authors: see the [original model card](https://huggingface.co/BAAI/bge-reranker-base) for what it does, how it was trained, and how to cite it.
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
  ## Files
16
 
17
  Copied byte for byte from:
18
 
19
- | File | Copied from | SHA-256 | Bytes |
20
  |---|---|---|---|
21
  | `onnx/model_int8.onnx` | [Xenova/bge-reranker-base](https://huggingface.co/Xenova/bge-reranker-base) | `2059d8ef0b6e935b4845e11b38c9af9e9e2e7b91f69fc99efe03254e0a7da8d3` | 278,825,308 |
22
  | `tokenizer.json` | [Xenova/bge-reranker-base](https://huggingface.co/Xenova/bge-reranker-base) | `48564c5c7d3fa64d85d95e65414a542385f88b0f128fd8d4163fd7a57f2be05c` | 17,098,079 |
23
 
24
- ## Licence
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
26
- MIT, the same as the original model (see `LICENSE`).
 
1
  ---
2
  license: mit
3
  base_model: BAAI/bge-reranker-base
4
+ pipeline_tag: text-ranking
5
+ library_name: onnx
6
  tags:
7
  - dakera
8
+ - ai-agent-memory
9
+ - agent-memory
10
+ - long-term-memory
11
+ - rag
12
+ - self-hosted
13
+ - mcp
14
+ - onnx
15
  - mirror
16
  ---
17
 
18
+ <p align="center">
19
+ <a href="https://dakera.ai"><img src="https://dakera.ai/assets/logo-128.png" width="96" alt="Dakera logo"></a>
20
+ </p>
21
 
22
+ <h1 align="center">bge-reranker-base</h1>
23
 
24
+ <p align="center"><b>Lighter reranker for Dakera 路 a verified mirror by Dakera, the self-hosted memory engine for AI agents</b></p>
25
+
26
+ <p align="center">
27
+ <a href="https://dakera.ai"><img alt="Dakera: dakera.ai" src="https://img.shields.io/badge/Dakera-dakera.ai-c9a227?style=flat-square"></a> <a href="https://dakera.ai/docs"><img alt="Docs: dakera.ai/docs" src="https://img.shields.io/badge/Docs-dakera.ai%2Fdocs-0b0b0b?style=flat-square"></a> <a href="https://github.com/Dakera-AI"><img alt="GitHub: Dakera-AI" src="https://img.shields.io/badge/GitHub-Dakera--AI-181717?style=flat-square&logo=github&logoColor=white"></a> <a href="https://huggingface.co/DakeraAI/bge-reranker-base/blob/main/LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-2b6cb0?style=flat-square"></a> <a href="https://huggingface.co/BAAI/bge-reranker-base"><img alt="Original: BAAI/bge-reranker-base" src="https://img.shields.io/badge/Original-BAAI%2Fbge--reranker--base-6b7280?style=flat-square"></a>
28
+ </p>
29
+
30
+
31
+ > An unmodified, checksum-verified copy of the files [Dakera](https://dakera.ai) uses from [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base). The model is by **BAAI**; all credit goes to its authors.
32
+
33
+ ## In Dakera
34
+
35
+ A smaller English cross-encoder reranker: `DAKERA_RERANKER_MODEL=bge-reranker-base`.
36
+
37
+ Dakera fetches this reranker from this repository first and from the original repositories if it is unreachable, so installs never depend on a single source. Both are checked against the same SHA-256, and the [Dakera Docker image](https://github.com/Dakera-AI/dakera-deploy) ships the default models ready to run, with no download at startup.
38
 
39
  ## Files
40
 
41
  Copied byte for byte from:
42
 
43
+ | File | Source | SHA-256 | Bytes |
44
  |---|---|---|---|
45
  | `onnx/model_int8.onnx` | [Xenova/bge-reranker-base](https://huggingface.co/Xenova/bge-reranker-base) | `2059d8ef0b6e935b4845e11b38c9af9e9e2e7b91f69fc99efe03254e0a7da8d3` | 278,825,308 |
46
  | `tokenizer.json` | [Xenova/bge-reranker-base](https://huggingface.co/Xenova/bge-reranker-base) | `48564c5c7d3fa64d85d95e65414a542385f88b0f128fd8d4163fd7a57f2be05c` | 17,098,079 |
47
 
48
+ ## Licence and credit
49
+
50
+ MIT, the same as the original model (see [`LICENSE`](https://huggingface.co/DakeraAI/bge-reranker-base/blob/main/LICENSE)). For what the model does, how it was trained and how to cite it, see the [original model card](https://huggingface.co/BAAI/bge-reranker-base).
51
+
52
+ ## About Dakera
53
+
54
+ **[Dakera](https://dakera.ai) is a self-hosted memory engine for AI agents.** It gives agents long-term memory that survives sessions: hybrid vector and full-text retrieval, reranking, entity extraction and importance decay, in a single Rust binary that runs on your own servers, with an MCP server for Claude, Cursor and other agents. 88.2% Recall@20 on the LoCoMo long-term memory benchmark.
55
+
56
+ ```bash
57
+ docker run -p 3000:3000 -e DAKERA_ROOT_API_KEY=dk-mykey ghcr.io/dakera-ai/dakera:latest
58
+ ```
59
+
60
+ | | |
61
+ |---|---|
62
+ | 馃寪 Website | [dakera.ai](https://dakera.ai) |
63
+ | 馃摎 Documentation | [dakera.ai/docs](https://dakera.ai/docs) |
64
+ | 馃捇 GitHub | [github.com/Dakera-AI](https://github.com/Dakera-AI) |
65
+ | 馃殌 Self-hosting (Docker, Kubernetes, Helm) | [dakera-deploy](https://github.com/Dakera-AI/dakera-deploy) |
66
+ | 馃攲 MCP server | [dakera-mcp](https://github.com/Dakera-AI/dakera-mcp) |
67
+ | 馃О SDKs | [Python](https://github.com/Dakera-AI/dakera-py) 路 [TypeScript](https://github.com/Dakera-AI/dakera-js) 路 [Go](https://github.com/Dakera-AI/dakera-go) 路 [Rust](https://github.com/Dakera-AI/dakera-rs) |
68
+ | 馃捈 LinkedIn | [Dakera AI](https://www.linkedin.com/company/dakera-ai) |
69
 
70
+ Questions or feedback: [amine@dakera.ai](mailto:amine@dakera.ai).