Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,7 @@ language:
|
|
| 33 |
|
| 34 |
This repo is the Mixedbread reranker rewritten as Classifier that is as of March 2025 the most powerful reranker, e.g. for RAG.
|
| 35 |
|
| 36 |
-
# FP8 Deployment on H100
|
| 37 |
|
| 38 |
```yaml
|
| 39 |
build_commands: []
|
|
@@ -57,7 +57,7 @@ trt_llm:
|
|
| 57 |
build:
|
| 58 |
base_model: encoder
|
| 59 |
checkpoint_repository:
|
| 60 |
-
repo: michaelfeil/mxbai-rerank-
|
| 61 |
revision: main
|
| 62 |
source: HF
|
| 63 |
max_num_tokens: 32768
|
|
@@ -68,6 +68,8 @@ trt_llm:
|
|
| 68 |
|
| 69 |
To push the deployment on Baseten.co
|
| 70 |
```bash
|
|
|
|
|
|
|
| 71 |
truss push --publish
|
| 72 |
```
|
| 73 |
More info:
|
|
|
|
| 33 |
|
| 34 |
This repo is the Mixedbread reranker rewritten as Classifier that is as of March 2025 the most powerful reranker, e.g. for RAG.
|
| 35 |
|
| 36 |
+
# FP8 Deployment on NVIDIA L4/H100
|
| 37 |
|
| 38 |
```yaml
|
| 39 |
build_commands: []
|
|
|
|
| 57 |
build:
|
| 58 |
base_model: encoder
|
| 59 |
checkpoint_repository:
|
| 60 |
+
repo: michaelfeil/mxbai-rerank-large-v2-seq
|
| 61 |
revision: main
|
| 62 |
source: HF
|
| 63 |
max_num_tokens: 32768
|
|
|
|
| 68 |
|
| 69 |
To push the deployment on Baseten.co
|
| 70 |
```bash
|
| 71 |
+
pip install truss --upgrade
|
| 72 |
+
nano config.yaml # above config
|
| 73 |
truss push --publish
|
| 74 |
```
|
| 75 |
More info:
|