Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,19 @@ library_name: peft
|
|
7 |
|
8 |
This is a reproduced version of the RepLLaMA model. See [this thread](https://github.com/texttron/tevatron/issues/129) for details of the reproduction process, which changed from their original version.
|
9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
You can use this with the RepLLaMA example code in [tevatron](https://github.com/texttron/tevatron) or with mteb:
|
11 |
|
12 |
```python
|
@@ -50,4 +63,15 @@ deepspeed --include localhost:0,1,2,3 --master_port 60000 --module tevatron.retr
|
|
50 |
--gradient_accumulation_steps 4
|
51 |
```
|
52 |
|
53 |
-
For citation, please also see the [original RepLLaMA paper](https://arxiv.org/abs/2310.08319)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
|
8 |
This is a reproduced version of the RepLLaMA model. See [this thread](https://github.com/texttron/tevatron/issues/129) for details of the reproduction process, which changed from their original version.
|
9 |
|
10 |
+
# Other Links
|
11 |
+
| Binary | Description |
|
12 |
+
|:-------|:------------|
|
13 |
+
| [samaya-ai/promptriever-llama2-7b-v1](https://huggingface.co/samaya-ai/promptriever-llama2-7b-v1) | A Promptriever bi-encoder model based on LLaMA 2 (7B parameters).|
|
14 |
+
| [samaya-ai/promptriever-llama3.1-8b-instruct-v1](https://huggingface.co/samaya-ai/promptriever-llama3.1-8b-instruct-v1) | A Promptriever bi-encoder model based on LLaMA 3.1 Instruct (8B parameters).|
|
15 |
+
| [samaya-ai/promptriever-llama3.1-8b-v1](https://huggingface.co/samaya-ai/promptriever-llama3.1-8b-v1) | A Promptriever bi-encoder model based on LLaMA 3.1 (8B parameters).|
|
16 |
+
| [samaya-ai/promptriever-mistral-v0.1-7b-v1](https://huggingface.co/samaya-ai/promptriever-mistral-v0.1-7b-v1) | A Promptriever bi-encoder model based on Mistral v0.1 (7B parameters). |
|
17 |
+
| [samaya-ai/RepLLaMA-reproduced](https://huggingface.co/samaya-ai/RepLLaMA-reproduced) | A reproduction of the RepLLaMA model (no instructions). A bi-encoder based on LLaMA 2, trained on the [tevatron/msmarco-passage-aug](https://huggingface.co/datasets/Tevatron/msmarco-passage-aug) dataset. |
|
18 |
+
| [samaya-ai/msmarco-w-instructions](https://huggingface.co/samaya-ai/msmarco-w-instructions) | A dataset of MS MARCO with added instructions and instruction-negatives, used for training the above models. |
|
19 |
+
|
20 |
+
|
21 |
+
# Usage
|
22 |
+
|
23 |
You can use this with the RepLLaMA example code in [tevatron](https://github.com/texttron/tevatron) or with mteb:
|
24 |
|
25 |
```python
|
|
|
63 |
--gradient_accumulation_steps 4
|
64 |
```
|
65 |
|
66 |
+
For citation, please also see the [original RepLLaMA paper](https://arxiv.org/abs/2310.08319) and feel free to cite Promptriever as well:
|
67 |
+
|
68 |
+
# Citation
|
69 |
+
|
70 |
+
```bibtex
|
71 |
+
@article{weller2024promptriever,
|
72 |
+
title={Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models},
|
73 |
+
author={Weller, Orion and Van Durme, Benjamin and Lawrie, Dawn and Paranjape, Ashwin and Zhang, Yuhao and Hessel, Jack},
|
74 |
+
journal={arXiv preprint TODO},
|
75 |
+
year={2024}
|
76 |
+
}
|
77 |
+
```
|