Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
dwadden commited on
Commit
c745b33
·
verified ·
1 Parent(s): a4cc39e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -8,8 +8,6 @@ language:
8
  ---
9
  # Model Card for SciTulu 7B
10
 
11
- <img src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/scitulu/scitulu_camel.png" alt="SciTulu logo" width="300" align="right"/>
12
-
13
  SciTulu is a collection of instruction-following language models targeting scientific literature understanding use cases. Starting from the [Tulu v2 7B](https://huggingface.co/allenai/tulu-2-7b) model, SciTulu is trained on a mix of science-specific demonstrations from the [SciRIFF dataset](https://huggingface.co/datasets/allenai/SciRIFF-train-mix), together with general-domain instructions from the [Tulu v2 SFT mix](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture). SciTulu 7B achives a 28.1% average improvement over Tulu v2 7B on nine held-out scientific literature understanding tasks. More information can be found in our preprint: [SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature](https://arxiv.org/abs/2406.07835).
14
 
15
  Training and evaluation code for SciTulu is available in our GitHub repository: https://huggingface.co/datasets/allenai/SciRIFF.
 
8
  ---
9
  # Model Card for SciTulu 7B
10
 
 
 
11
  SciTulu is a collection of instruction-following language models targeting scientific literature understanding use cases. Starting from the [Tulu v2 7B](https://huggingface.co/allenai/tulu-2-7b) model, SciTulu is trained on a mix of science-specific demonstrations from the [SciRIFF dataset](https://huggingface.co/datasets/allenai/SciRIFF-train-mix), together with general-domain instructions from the [Tulu v2 SFT mix](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture). SciTulu 7B achives a 28.1% average improvement over Tulu v2 7B on nine held-out scientific literature understanding tasks. More information can be found in our preprint: [SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature](https://arxiv.org/abs/2406.07835).
12
 
13
  Training and evaluation code for SciTulu is available in our GitHub repository: https://huggingface.co/datasets/allenai/SciRIFF.