Muennighoff commited on
Commit
9389134
1 Parent(s): a1475bd

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-generation
3
+ inference: true
4
+ license: apache-2.0
5
+ datasets:
6
+ - GritLM/tulu2
7
+
8
+ ---
9
+
10
+ # Model Summary
11
+
12
+ A [**KTO**](https://arxiv.org/abs/2402.01306) version of https://huggingface.co/GritLM/GritLM-8x7B
13
+
14
+ > GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.
15
+
16
+ - **Repository:** [ContextualAI/gritlm](https://github.com/ContextualAI/gritlm)
17
+ - **Paper:** https://arxiv.org/abs/2402.09906
18
+ - **Logs:** https://wandb.ai/muennighoff/gritlm/runs/0uui712t/overview
19
+ - **Script:** https://github.com/ContextualAI/gritlm/blob/main/scripts/training/train_gritlm_7b.sh
20
+
21
+ | Model | Description |
22
+ |-------|-------------|
23
+ | [GritLM 7B](https://hf.co/GritLM/GritLM-7B) | Mistral 7B finetuned using GRIT |
24
+ | [GritLM 8x7B](https://hf.co/GritLM/GritLM-8x7B) | Mixtral 8x7B finetuned using GRIT |
25
+
26
+ # Use
27
+
28
+ The model usage is documented [here](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference).
29
+
30
+ # Citation
31
+
32
+ ```bibtex
33
+ @misc{muennighoff2024generative,
34
+ title={Generative Representational Instruction Tuning},
35
+ author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},
36
+ year={2024},
37
+ eprint={2402.09906},
38
+ archivePrefix={arXiv},
39
+ primaryClass={cs.CL}
40
+ }
41
+ ```