Update README.md

README.md

@@ -7,30 +7,42 @@ language:
 - en
 ---
 # Instruction Pre-Training: Language Models are Supervised Multitask Learners
-This repo contains the **instruction-pretrained base model** in our paper **Instruction Pre-Training: Language Models are Supervised Multitask Learners**.
+This repo contains the **general models pre-trained from scratch** in our paper **Instruction Pre-Training: Language Models are Supervised Multitask Learners**.
 
-We explore supervised multitask pre-training by proposing ***Instruction Pre-Training***, a framework that scalably augments massive raw corpora with instruction-response pairs to pre-train language models. The instruction-response pairs are generated by an efficient instruction synthesizer built on open-source models. In our experiments, we synthesize 200M instruction-response pairs covering 40+ task categories to verify the effectiveness of *Instruction Pre-Training*. Instruction Pre-Training* outperforms *Vanilla Pre-training* in both general pre-training from scratch and domain-adaptive continued pre-training. **In pre-training from scratch, *Instruction Pre-Training* not only improves pre-trained base models but also benefits more from further instruction tuning.** In continual pre-training, *Instruction Pre-Training* enables Llama3-8B to be comparable to or even outperform Llama3-70B.
+We explore supervised multitask pre-training by proposing ***Instruction Pre-Training***, a framework that scalably augments massive raw corpora with instruction-response pairs to pre-train language models. The instruction-response pairs are generated by an efficient instruction synthesizer built on open-source models. In our experiments, we synthesize 200M instruction-response pairs covering 40+ task categories to verify the effectiveness of *Instruction Pre-Training*. Instruction Pre-Training* outperforms *Vanilla Pre-training* in both general pre-training from scratch and domain-adaptive continual pre-training. **In pre-training from scratch, *Instruction Pre-Training* not only improves pre-trained base models but also benefits more from further instruction tuning.** In continual pre-training, *Instruction Pre-Training* enables Llama3-8B to be comparable to or even outperform Llama3-70B.
 
 <p align='center'>
-    <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/j1hlqGreoZrBsK7sz3oG9.png" width="500">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/vRdsFIVQptbNaGiZ18Lih.png" width="400">
 </p>
 
+## Resources
+**🤗 We share our data and models with example usages, feel free to open any issues or discussions! 🤗**
+
+- Context-Based Instruction Synthesizer: [instruction-synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer)
+- Fine-Tuning Data for the Synthesizer: [ft-instruction-synthesizer-collection](https://huggingface.co/datasets/instruction-pretrain/ft-instruction-synthesizer-collection)
+- General Models Pre-Trained from Scratch:
+  - [InstructLM-500M](https://huggingface.co/instruction-pretrain/InstructLM-500M)
+  - [InstructLLM-1.3B](https://huggingface.co/instruction-pretrain/InstructLLM-1.3B)
+- Domain-Specific Models Pre-Trained from Llama3-8B:
+  - [Finance-Llama3-8B](https://huggingface.co/instruction-pretrain/finance-Llama3-8B)
+  - [Biomedicine-Llama3-8B](https://huggingface.co/instruction-pretrain/medicine-Llama3-8B)
+
 ## General Pre-Training From Scratch
-We augment the RefinedWeb corproa with instruction-response pairs generated by our [context-based instruction synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer) to pre-train a general langauge model from scratch.
+We augment the [RefinedWeb corproa](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) with instruction-response pairs generated by our [context-based instruction synthesizer](https://huggingface.co/instruction-pretrain/instruction-synthesizer) to pre-train general langauge models from scratch.
 
 To evaluate our general base model using the [lm-evaluation-harness framework](https://github.com/EleutherAI/lm-evaluation-harness)
 
-1. Setup dependencies
+1. Setup dependencies:
 ```bash
 git clone https://github.com/EleutherAI/lm-evaluation-harness
 cd lm-evaluation-harness
 pip install -e .
 ```
 
-2. Evalaute
+2. Evalaute:
 ```bash
 MODEL=instruction-pretrain/InstructLM-500M
-add_bos_token=True # this flag is needed because lm-eval-harness set add_bos_token to False by default, but ours requires add_bos_token to be True
+add_bos_token=True # this flag is needed because lm-eval-harness set add_bos_token to False by default, but ours require add_bos_token to be True
 
 accelerate launch -m lm_eval --model hf \
     --model_args pretrained=${MODEL},add_bos_token=${add_bos_token},dtype=float16  \
@@ -50,7 +62,7 @@ accelerate launch -m lm_eval --model hf \
 ## Citation
 If you find our work helpful, please cite us:
 
-[AdaptLLM](https://huggingface.co/papers/2309.09530):
+[AdaptLLM](https://huggingface.co/papers/2309.09530)
 ```bibtex
 @inproceedings{
 cheng2024adapting,