Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,12 @@ pipeline_tag: text-ranking
|
|
| 12 |
|
| 13 |
This is a compressed version of tomaarsen/Qwen3-Reranker-0.6B-seq-cls using llm-compressor with the following scheme: W8A8
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Model Details
|
| 16 |
|
| 17 |
- **Original Model**: tomaarsen/Qwen3-Reranker-0.6B-seq-cls
|
|
|
|
| 12 |
|
| 13 |
This is a compressed version of tomaarsen/Qwen3-Reranker-0.6B-seq-cls using llm-compressor with the following scheme: W8A8
|
| 14 |
|
| 15 |
+
## Serving
|
| 16 |
+
|
| 17 |
+
``python3 -m vllm.entrypoints.openai.api_server --download-dir '/data' --model 'dolfsai/Qwen3-Reranker-0.6B-seq-cls-vllm-W8A8' --task classify``
|
| 18 |
+
|
| 19 |
+
**Important**: You MUST read the following guide for correct usage of this model here [Guide](https://github.com/vllm-project/vllm/pull/19260)
|
| 20 |
+
|
| 21 |
## Model Details
|
| 22 |
|
| 23 |
- **Original Model**: tomaarsen/Qwen3-Reranker-0.6B-seq-cls
|