Text Generation
Transformers
English
query-rewriting
reasoning
retrieval
BRIGHT
GRPO
alignment
Eval Results (legacy)
Instructions to use ForwardAILabs/MQR-A1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ForwardAILabs/MQR-A1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ForwardAILabs/MQR-A1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ForwardAILabs/MQR-A1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ForwardAILabs/MQR-A1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ForwardAILabs/MQR-A1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ForwardAILabs/MQR-A1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ForwardAILabs/MQR-A1
- SGLang
How to use ForwardAILabs/MQR-A1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ForwardAILabs/MQR-A1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ForwardAILabs/MQR-A1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ForwardAILabs/MQR-A1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ForwardAILabs/MQR-A1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ForwardAILabs/MQR-A1 with Docker Model Runner:
docker model run hf.co/ForwardAILabs/MQR-A1
Update README.md
Browse files
README.md
CHANGED
|
@@ -37,6 +37,13 @@ model-index:
|
|
| 37 |
name: nDCG@10
|
| 38 |
---
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
# MQR-A1: Mira Query Rewriter — Alignment v1
|
| 41 |
|
| 42 |
**MQR-A1** (Mira Query Rewriter, Alignment v1) is a GRPO-aligned query rewriting model designed for reasoning-intensive retrieval tasks. It is the alignment component of our retrieval pipeline: by rewriting queries to distill core retrieval intents and filter misleading noise, MQR-A1 enables the downstream retriever [MRE-T1](https://huggingface.co/ForwardAILabs/MRE-T1) to achieve state-of-the-art performance.
|
|
|
|
| 37 |
name: nDCG@10
|
| 38 |
---
|
| 39 |
|
| 40 |
+
<div align="center">
|
| 41 |
+
<h3>Built by <a href="https://huggingface.co/ForwardAILabs">Forward AI Labs</a></h3>
|
| 42 |
+
<p>We are an AI company that provides recruitment agents. | <a href="https://www.mira.day/">mira.day</a></p>
|
| 43 |
+
</div>
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
# MQR-A1: Mira Query Rewriter — Alignment v1
|
| 48 |
|
| 49 |
**MQR-A1** (Mira Query Rewriter, Alignment v1) is a GRPO-aligned query rewriting model designed for reasoning-intensive retrieval tasks. It is the alignment component of our retrieval pipeline: by rewriting queries to distill core retrieval intents and filter misleading noise, MQR-A1 enables the downstream retriever [MRE-T1](https://huggingface.co/ForwardAILabs/MRE-T1) to achieve state-of-the-art performance.
|