license: apache-2.0
datasets:
- allenai/dolmino-mix-1124
- allenai/dolma
language:
- en
Model Details
Model Card for OLMo2 7B
OLMo2 7B November 2024 is an updated version of the original OLMo 7B model rocking a ____ point increase in ____, among other evaluations improvements, from an improved version of the Dolma dataset and staged training.
OLMo is a series of Open Language Models designed to enable the science of language models. These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs (coming soon), and associated training details. The core models released in this batch include the following:
| Size | Training Tokens | Layers | Hidden Size | Attention Heads | Context Length |
|---|---|---|---|---|---|
| OLMo2-7B | 4 Trillion | 32 | 4096 | 32 | 4096 |
| OLMo2- 13B | 5 Trillion | 40 | 5120 | 42 | 4096 |
Inference
You can use OLMo with the standard HuggingFace transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-1124-7B")
message = ["Language modeling is "]
inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
# optional verifying cuda
# inputs = {k: v.to('cuda') for k,v in inputs.items()}
# olmo = olmo.to('cuda')
response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
>> 'Language modeling is the first step to build natural language generation...'
For faster performance, you can quantize the model using the following method:
AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B",
torch_dtype=torch.float16,
load_in_8bit=True) # Requires bitsandbytes
The quantized model is more sensitive to data types and CUDA operations. To avoid potential issues, it's recommended to pass the inputs directly to CUDA using:
inputs.input_ids.to('cuda')
We have released checkpoints for these models, for every 1000 training steps.
The naming convention is stepXXX-tokensYYYB.
To load a specific model revision with HuggingFace, simply add the argument revision:
olmo = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-1124-7B", revision="step1000-tokens5B")
Or, you can access all the revisions for the models via the following code snippet:
from huggingface_hub import list_repo_refs
out = list_repo_refs("allenai/OLMo-2-1124-7B")
branches = [b.name for b in out.branches]
Fine-tuning
Model fine-tuning can be done from the final checkpoint (the main revision of this model) or many intermediate checkpoints. Two recipes for tuning are available.
- Fine-tune with the OLMo repository:
torchrun --nproc_per_node=8 scripts/train.py {path_to_train_config} \
--data.paths=[{path_to_data}/input_ids.npy] \
--data.label_mask_paths=[{path_to_data}/label_mask.npy] \
--load_path={path_to_checkpoint} \
--reset_trainer_state
For more documentation, see the GitHub readme.
- Further fine-tuning support is being developing in AI2's Open Instruct repository. Details are here.
Model Description
- Developed by: Allen Institute for AI (Ai2)
- Supported by: Databricks, Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, AMD, CSC (Lumi Supercomputer), UW
- Model type: a Transformer style autoregressive language model.
- Language(s) (NLP): English
- License: The code and model are released under Apache 2.0.
- Contact: Technical inquiries:
olmo at allenai dot org. Press:press at allenai dot org - Date cutoff: Oct. 2023, with most data from Feb./March 2023 based on Dolma dataset version.
Model Sources
- Project Page: https://allenai.org/olmo
- Repositories:
- Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo
- Evaluation code: https://github.com/allenai/OLMo-Eval
- Further fine-tuning code: https://github.com/allenai/open-instruct
Evaluation
Core model results for OLMo2 7B and 13B models are found below.
| Model | Train FLOPs | Average | ARC/C | HSwag | WinoG | MMLU | DROP | NQ | AGIEval | GSM8k | MMWLUPro | TriviaQA |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemma-2-9B | 4.4·10²³ | 52.9 | 89.5 | 87.3 | 78.8 | 70.6 | 63 | 38 | 57.3 | 1.1 | 42 | 0.9 |
| Llama-2-13B | 1.6·10²³ | 54.1 | 67.3 | 83.9 | 74.9 | 55.7 | 45.6 | 38.4 | 41.5 | 28.1 | 23.9 | 81.3 |
| Mistral-7B-v0.3 | n/a | 58.8 | 78.3 | 83.1 | 77.7 | 63.5 | 51.8 | 37.2 | 47.3 | 40.1 | 30 | 79.3 |
| Llama-3.1-8B | 7.2·10²³ | 61.8 | 79.5 | 81.6 | 76.6 | 66.9 | 56.4 | 33.9 | 51.3 | 56.5 | 34.7 | 80.3 |
| Mistral-Nemo-12B | n/a | 66.9 | 85.2 | 85.6 | 81.5 | 69.5 | 69.2 | 39.7 | 54.7 | 62.1 | 36.7 | 84.6 |
| Qwen-2.5-7B | 8.2·10²³ | 67.4 | 89.5 | 89.7 | 74.2 | 74.4 | 55.8 | 29.9 | 63.7 | 81.5 | 45.8 | 69.4 |
| Qwen-2.5-14B | 16.0·10²³ | 72.2 | 94 | 94 | 80 | 79.3 | 51.5 | 37.3 | 71 | 83.4 | 52.8 | 79.1 |
| StableLM-2-12B | 2.9·10²³ | 62.2 | 81.9 | 84.5 | 77.7 | 62.4 | 55.5 | 37.6 | 50.9 | 62 | 29.3 | 79.9 |
| Zamba-2-7B | n/c | 65.2 | 92.2 | 89.4 | 79.6 | 68.5 | 51.7 | 36.5 | 55.5 | 67.2 | 32.8 | 78.8 |
| Amber-7B | 0.5·10²³ | 35.2 | 44.9 | 74.5 | 65.5 | 24.7 | 26.1 | 18.7 | 21.8 | 4.8 | 11.7 | 59.3 |
| OLMo-7B | 1.0·10²³ | 38.3 | 46.4 | 78.1 | 68.5 | 28.3 | 27.3 | 24.8 | 23.7 | 9.2 | 12.1 | 64.1 |
| MAP-Neo-7B | 2.1·10²³ | 49.6 | 78.4 | 72.8 | 69.2 | 58 | 39.4 | 28.9 | 45.8 | 12.5 | 25.9 | 65.1 |
| OLMo-0424-7B | 0.9·10²³ | 50.7 | 66.9 | 80.1 | 73.6 | 54.3 | 50 | 29.6 | 43.9 | 27.7 | 22.1 | 58.8 |
| DCLM-7B | 1.0·10²³ | 56.9 | 79.8 | 82.3 | 77.3 | 64.4 | 39.3 | 28.8 | 47.5 | 46.1 | 31.3 | 72.1 |
| OLMo-2-1124-7B | 1.8·10²³ | 62.9 | 79.8 | 83.8 | 77.2 | 63.7 | 60.8 | 36.9 | 50.4 | 67.5 | 31 | 78 |
| OLMo-2-1124-13B | 4.6·10²³ | 68.3 | 83.5 | 86.4 | 81.5 | 67.5 | 70.7 | 46.7 | 54.2 | 75.1 | 35.1 | 81.9 |
Model Details
Pretraining
| OLMo 2 7B | OLMo 2 13B | |
|---|---|---|
| Pretraining Stage 1 (OLMo-Mix-1124) |
4 trillion tokens (1 epoch) |
5 trillion tokens (1.2 epochs) |
| Pretraining Stage 2 (Dolmino-Mix-1124) |
50B tokens (3 runs) merged |
100B tokens (3 runs) 300B tokens (1 run) merged |
| Post-training (Tulu 3 SFT OLMo mix) |
SFT + DPO + PPO (preference mix) |
SFT + DPO + PPO (preference mix) |
Stage 1: Initial Pretraining
- Dataset: OLMo-Mix-1124 (3.9T tokens)
- Coverage: 90%+ of total pretraining budget
- 7B Model: ~1 epoch
- 13B Model: 1.2 epochs (5T tokens)
Stage 2: Fine-tuning
- Dataset: Dolmino-Mix-1124 (843B tokens)
- Three training mixes:
- 50B tokens
- 100B tokens
- 300B tokens
- Mix composition: 50% high-quality data + academic/Q&A/instruction/math content
Model Merging
- 7B Model: 3 versions trained on 50B mix, merged via model souping
- 13B Model: 3 versions on 100B mix + 1 version on 300B mix, merged for final checkpoint
Bias, Risks, and Limitations
Like any base language model or fine-tuned model without safety filtering, these models can easily be prompted by users to generate harmful and sensitive content. Such content may also be produced unintentionally, especially in cases involving bias, so we recommend that users consider the risks when applying this technology. Additionally, many statements from OLMo or any LLM are often inaccurate, so facts should be verified.
Citation
TODO
Model Card Contact
For errors in this model card, contact Aman, {amanr} at allenai dot org.