Upload 8 files

README.md

@@ -1,3 +1,53 @@
----
-license: apache-2.0
----
+# Instruction Pre-Training: Language Models are Supervised Multitask Learners
+This repo contains the **context-based instruction synthesizer** used 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.
+
+<p align='center'>
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/66711d2ee12fa6cc5f5dfc89/j1hlqGreoZrBsK7sz3oG9.png" width="500">
+</p>
+
+## 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.
+
+To evaluate our general base model using the [lm-evaluation-harness framework](https://github.com/EleutherAI/lm-evaluation-harness)
+
+1. Setup dependencies:
+```bash
+git clone https://github.com/EleutherAI/lm-evaluation-harness
+cd lm-evaluation-harness
+pip install -e .
+```
+
+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 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  \
+    --gen_kwargs do_sample=False \
+    --tasks piqa,hellaswag,winogrande \
+    --batch_size auto \
+    --num_fewshot 0
+
+accelerate launch -m lm_eval --model hf \
+    --model_args pretrained=${MODEL},add_bos_token=${add_bos_token},dtype=float16 \
+    --gen_kwargs do_sample=False \
+    --tasks social_iqa,ai2_arc,openbookqa,boolq,mmlu \
+    --batch_size auto \
+    --num_fewshot 5
+```
+
+## Citation
+If you find our work helpful, please cite us:
+```bibtex
+@inproceedings{
+cheng2024adapting,
+title={Adapting Large Language Models via Reading Comprehension},
+author={Daixuan Cheng and Shaohan Huang and Furu Wei},
+booktitle={The Twelfth International Conference on Learning Representations},
+year={2024},
+url={https://openreview.net/forum?id=y886UXPEZ0}
+}
+```

config.json

@@ -0,0 +1,24 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 4320,
+    "max_position_embeddings": 2048,
+    "model_type": "mistral",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 24,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 2048,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.34.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef58dc140a03cd4f99a0f72cbf9830d81d55138dc01a77b7e834ea6b82d72dc
+size 2271376918

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}