Feature Extraction
Transformers
English
retrieval
reasoning
embedding
BRIGHT
information-retrieval
Eval Results (legacy)
Instructions to use ForwardAILabs/MRE-T1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ForwardAILabs/MRE-T1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ForwardAILabs/MRE-T1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ForwardAILabs/MRE-T1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -43,9 +43,9 @@ model-index:
|
|
| 43 |
|
| 44 |
---
|
| 45 |
|
| 46 |
-
# MRE-T1: Mira
|
| 47 |
|
| 48 |
-
**MRE-T1** (Mira
|
| 49 |
|
| 50 |
MRE-T1 achieves state-of-the-art single-model performance on the [BRIGHT benchmark](https://brightbenchmark.github.io/), which evaluates retrieval models on tasks requiring complex reasoning capabilities.
|
| 51 |
|
|
|
|
| 43 |
|
| 44 |
---
|
| 45 |
|
| 46 |
+
# MRE-T1: Mira Reasoning Embedding — Thought v1
|
| 47 |
|
| 48 |
+
**MRE-T1** (Mira Reasoning Embedding, Thought v1) is the first generation of our reasoning-intensive retrieval model series. The "Thought" in T1 reflects the model's core capability — it thinks before it retrieves, generating explicit reasoning chains to deeply understand query intent before producing embeddings.
|
| 49 |
|
| 50 |
MRE-T1 achieves state-of-the-art single-model performance on the [BRIGHT benchmark](https://brightbenchmark.github.io/), which evaluates retrieval models on tasks requiring complex reasoning capabilities.
|
| 51 |
|