license: apache-2.0
datasets:
- allenai/dolmino-mix-1124
- allenai/olmo-mix-1124
language:
- en
base_model: allenai/OLMo-2-1124-7B
tags:
- llama-cpp
- gguf-my-repo
Triangle104/OLMo-2-1124-7B-Q8_0-GGUF
This model was converted to GGUF format from allenai/OLMo-2-1124-7B using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Model details:
We introduce OLMo 2, a new family of 7B and 13B models featuring a 9-point increase in MMLU, among other evaluation improvements, compared to the original OLMo 7B model. These gains come from training on OLMo-mix-1124 and Dolmino-mix-1124 datasets and staged training approach.
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.
Installation
OLMo 2 will be supported in the next version of Transformers, and you need to install it from the main branch using:
pip install --upgrade git+https://github.com/huggingface/transformers.git
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 a key component of any text-based application, but its effectiveness...'
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 pretraining, the naming convention is stepXXX-tokensYYYB. For checkpoints with ingredients of the soup, the naming convention is stage2-ingredientN-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) 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: [email protected]. Press: [email protected] Date cutoff: Dec. 2023.
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
Paper: Coming soon
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
A technical manuscript is forthcoming!
Model Card Contact
For errors in this model card, contact [email protected].
Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
CLI:
llama-cli --hf-repo Triangle104/OLMo-2-1124-7B-Q8_0-GGUF --hf-file olmo-2-1124-7b-q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Triangle104/OLMo-2-1124-7B-Q8_0-GGUF --hf-file olmo-2-1124-7b-q8_0.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggerganov/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo Triangle104/OLMo-2-1124-7B-Q8_0-GGUF --hf-file olmo-2-1124-7b-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Triangle104/OLMo-2-1124-7B-Q8_0-GGUF --hf-file olmo-2-1124-7b-q8_0.gguf -c 2048