Unsloth Dynamic 2.0 具备更高的精度,并优于其他主流量化方案。
我们推出 Olmo 3,这是一个全新的 7B 与 32B 模型系列,均提供 Instruct 和 Think 两种变体。长思维链可提升数学与编程等推理任务的表现。
Olmo 是一系列 Open language models,旨在推动语言模型科学的发展。 这些模型基于 Dolma 3 数据集进行预训练,并基于 Dolci 数据集进行后训练。我们将发布所有代码、检查点、日志(即将推出)以及相关训练细节。
本批次发布的核心模型如下:
| 阶段 | Olmo 3 7B Think | Olmo 3 32B Think | Olmo 3 7B Instruct |
|---|---|---|---|
| 基础模型 | Olmo-3-7B | Olmo-3-32B | Olmo-3-7B |
| SFT | Olmo-3-7B-Think-SFT | Olmo-3-32B-Think-SFT | Olmo-3-7B-Instruct-SFT |
| DPO | Olmo-3-7B-Think-DPO | Olmo-3-32B-Think-DPO | Olmo-3-7B-Instruct-DPO |
| 最终模型(RLVR) | Olmo-3-7B-Think | Olmo-3-32B-Think | Olmo-3-7B-Instruct |
Olmo 3 在 transformers 4.57.0 及更高版本中受到支持:
pip install transformers>=4.57.0你可以使用标准的 HuggingFace transformers 库来运行 OLMo:
from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-32B-Think")
tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-32B-Think")
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...'为获得更快的性能,您可以使用以下方法对模型进行量化:
AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-32B-Think",
torch_dtype=torch.float16,
load_in_8bit=True) # Requires bitsandbytes量化模型对数据类型和 CUDA 操作更为敏感。为避免潜在问题,建议通过以下方式将输入直接传入 CUDA:
inputs.input_ids.to('cuda')我们已为这些模型发布检查点。对于后训练,命名规则为 step_XXX。
若要在 HuggingFace 中加载某个特定的模型修订版本,只需添加参数 revision:
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-32B-Think", revision="step_300")或者,您可以通过以下代码片段访问这些模型的所有版本:
from huggingface_hub import list_repo_refs
out = list_repo_refs("allenai/Olmo-3-32B-Think")
branches = [b.name for b in out.branches]该模型的默认系统提示词为:
<|im_start|>system
You are a helpful AI assistant.<|im_end|>本模型的对话模板格式如下:
<|im_start|>system
You are a helpful AI assistant.
<|im_start|>user
Who would win in a fight - a dinosaur or a cow named Moo Moo?<|im_end|>
<|im_start|>assistant
<think>Okay, so the question is who would win in a fight between a dinosaur and a cow named Moo Moo.
Hmm, first I need to break this down. Let me think about the different factors involved here..... </think>
Moo Moo the cow would certinaly win.
<|endoftext|>olmo@allenai.org。媒体咨询:press@allenai.org| 基准测试 | Olmo 3 Think 32B SFT | Olmo 3 Think 32B DPO | Olmo 3 Think 32B | Qwen 3 32B | Qwen 3 VL 32B Thinking | Qwen 2.5 32B | Gemma 3 27B Instruct | Gemma 2 27B Instruct | Olmo 2 32B Instruct | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|---|---|---|---|---|---|---|---|
| 数学 | ||||||||||
| MATH | 95.6 | 95.9 | 96.1 | 95.4 | 96.7 | 80.2 | 87.4 | 51.5 | 49.2 | 92.6 |
| AIME 2024 | 73.5 | 76.0 | 76.8 | 80.8 | 86.3 | 15.7 | 28.9 | 4.7 | 4.6 | 70.3 |
| AIME 2025 | 66.2 | 70.7 | 72.5 | 70.9 | 78.8 | 13.4 | 22.9 | 0.9 | 0.9 | 56.3 |
| OMEGA | 43.1 | 45.2 | 50.8 | 47.7 | 50.8 | 19.2 | 24.0 | 9.1 | 9.8 | 38.9 |
| 推理 | ||||||||||
| BigBenchHard | 88.8 | 89.1 | 89.8 | 90.6 | 91.1 | 80.9 | 82.4 | 66.0 | 65.6 | 89.7 |
| ZebraLogic | 70.5 | 74.5 | 76.0 | 88.3 | 96.1 | 24.1 | 24.8 | 17.2 | 13.3 | 69.4 |
| AGI Eval English | 85.9 | 87.8 | 88.2 | 90.0 | 92.2 | 78.9 | 76.9 | 70.9 | 68.4 | 88.1 |
| 编程 | ||||||||||
| HumanEvalPlus | 90.0 | 91.6 | 91.4 | 91.2 | 90.6 | 82.6 | 79.2 | 67.5 | 44.4 | 92.3 |
| MBPP+ | 66.7 | 67.2 | 68.0 | 70.6 | 66.2 | 66.6 | 65.7 | 61.2 | 49.0 | 70.1 |
| LiveCodeBench v3 | 75.8 | 81.9 | 83.5 | 90.2 | 84.8 | 49.9 | 39.0 | 28.7 | 10.6 | 79.5 |
| 指令遵循 | ||||||||||
| IFEval | 83.9 | 80.6 | 89.0 | 86.5 | 85.5 | 81.9 | 85.4 | 62.1 | 85.8 | 78.7 |
| IFBench | 37.0 | 34.4 | 47.6 | 37.3 | 55.1 | 36.7 | 31.3 | 27.8 | 36.4 | 23.8 |
| 知识与问答 | ||||||||||
| MMLU | 85.3 | 85.2 | 85.4 | 88.8 | 90.1 | 84.6 | 74.6 | 76.1 | 77.1 | 88.0 |
| PopQA | 33.1 | 37.0 | 31.9 | 30.7 | 32.2 | 28.0 | 30.2 | 30.4 | 37.2 | 26.7 |
| GPQA | 55.7 | 57.6 | 58.1 | 67.3 | 67.4 | 44.6 | 45.0 | 39.9 | 36.4 | 61.8 |
| 对话 | ||||||||||
| AlpacaEval 2 LC | 69.1 | 78.6 | 74.2 | 75.6 | 80.9 | 81.9 | 65.5 | 39.8 | 38.0 | 26.2 |
| 安全 | 64.8 | 65.3 | 68.8 | 69.0 | 82.7 | 81.9 | 68.6 | 74.3 | 83.8 | 63.6 |
与任何基座语言模型或未进行安全过滤的微调模型一样,这些模型容易被用户提示生成有害和敏感内容。此类内容也可能无意中产生,尤其是在涉及偏见的情形下,因此建议用户在应用该技术时充分评估相关风险。此外,来自 OLMo 或任何 LLM 的许多表述往往并不准确,因此应当核实事实。
技术文章即将发布!
如发现本模型卡存在错误,请联系 olmo@allenai.org。