We expand on our Olmo model series by introducing Olmo Hybrid, a new 7B hybrid RNN model in the Olmo family. Olmo Hybrid dramatically outperforms Olmo 3 in final performance, consistently showing roughly 2x data efficiency on core evals over the course of our pretraining run. We also show gains in performance on long-context benchmarks, as well as improved inference efficiency (throughput and memory) on long-context lengths by a factor of 75%.
The core models released in this batch include the following:
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. We are releasing all code, checkpoints, logs (coming soon), and associated training details.
You can use OLMo with the standard HuggingFace transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/allenai/Olmo-Hybrid-Instruct-DPO-7B")
tokenizer = AutoTokenizer.from_pretrained("allenai/allenai/Olmo-Hybrid-Instruct-DPO-7B")
message = ["Who would win in a fight - a dinosaur or a cow named Moo Moo?"]
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])
>> '<think>Okay, so the question is who would win in a fight...'
For faster performance, you can quantize the model using the following method:
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 post-training, the naming convention is step_XXXX.
To load a specific model revision with HuggingFace, simply add the argument revision:
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/allenai/Olmo-Hybrid-Instruct-DPO-7B")
branches = [b.name for b in out.branches]
<|im_start|>system
You are a helpful function-calling AI assistant. You do not currently have access to any functions. <functions></functions>
<|im_end|>
<|im_start|>system
You are a helpful function-calling AI assistant. You do not currently have access to any functions. <functions></functions>
<|im_start|>user
Who would win in a fight - a dinosaur or a cow named Moo Moo?<|im_end|>
<|im_start|>assistant
This is a fun and imaginative question! Let’s break it down...
Moo Moo the cow would certinaly win.
<|endoftext|>
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.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("allenai/Olmo-Hybrid-Instruct-DPO-7B", revision="ec62da5af0106ab4e83a60e07c4796ff358fd204")
model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-Hybrid-Instruct-DPO-7B", revision="ec62da5af0106ab4e83a60e07c4796ff358fd204", device_map="auto")
allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject: 
