enginex-mlu370-any2any/transformers/docs/source/en/model_doc/olmo3.md

This model was released on {release_date} and added to Hugging Face Transformers on 2025-09-16.

OLMo3

Olmo3 is an improvement on OLMo2. More details will be released on soon.

Tip

Click on the OLMo3 models in the right sidebar for more examples of how to apply OLMo3 to different language tasks.

The example below demonstrates how to generate text with [Pipeline], [AutoModel] and from the command line.

import torch
from transformers import pipeline

pipe = pipeline(
    task="text-generation",
    model="allenai/TBA",
    dtype=torch.bfloat16,
    device=0,
)

result = pipe("Plants create energy through a process known as")
print(result)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "allenai/TBA"
)

model = AutoModelForCausalLM.from_pretrained(
    "allenai/TBA",
    dtype=torch.bfloat16,
    device_map="auto",
    attn_implementation="sdpa"
)
input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to(model.device)

output = model.generate(**input_ids, max_length=50, cache_implementation="static")
print(tokenizer.decode(output[0], skip_special_tokens=True))

echo -e "Plants create energy through a process known as" | transformers run --task text-generation --model allenai/TBA --device 0

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses torchao to only quantize the weights to 4-bits.

#pip install torchao
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig

torchao_config = TorchAoConfig(
    "int4_weight_only",
    group_size=128
)

tokenizer = AutoTokenizer.from_pretrained(
    "allenai/TBA"
)

model = AutoModelForCausalLM.from_pretrained(
    "allenai/TBA",
    quantization_config=torchao_config,
    dtype=torch.bfloat16,
    device_map="auto",
    attn_implementation="sdpa"
)
input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to(model.device)

output = model.generate(**input_ids, max_length=50, cache_implementation="static")
print(tokenizer.decode(output[0], skip_special_tokens=True))

Notes

• Load specific intermediate checkpoints by adding the revision parameter to [~PreTrainedModel.from_pretrained].

  from transformers import AutoModelForCausalLM
  
  model = AutoModelForCausalLM.from_pretrained("allenai/TBA", revision="stage1-step140000-tokens294B")
  

Olmo3Config

autodoc Olmo3Config

Olmo3ForCausalLM

autodoc Olmo3ForCausalLM

Olmo3Model

autodoc Olmo3Model - forward

Olmo3PreTrainedModel

autodoc Olmo3PreTrainedModel - forward