Welcome to the xGen-small family!

xGen-small (blog, arXiv) is an enterprise-ready compact LM that combines domain-focused data curation, scalable pre-training, length-extension, and RL fine-tuning to deliver long-context performance at predictable, low cost. This model release is for research purposes only.

Model Series

xGen-small comes in two sizes (4B and 9B) with two variants (pre-trained and post-trained):

Model	# Total Params	Context Length	Variant	Download
salesforce/xgen-small-4B-base-r	4B	128k	Pre-trained	🤗 Link
salesforce/xgen-small-4B-instruct-r	4B	128k	Post-trained	🤗 Link
salesforce/xgen-small-9B-base-r	9B	128k	Pre-trained	🤗 Link
salesforce/xgen-small-9B-instruct-r	9B	128k	Post-trained	🤗 Link

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Salesforce/xgen-small-4B-base-r"
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto"
).to(device)

prompt = "What is Salesforce?"
inputs = tokenizer(
    prompt,
    return_tensors="pt",
    padding=False,
    truncation=True
).to(device)

generated = model.generate(**inputs, max_new_tokens=32)
output = tokenizer.decode(
    generated[0],
    skip_special_tokens=True,
)
print(output)

Evaluation

Category	Task	Llama 3.2-3B	Gemma 3-4B	Qwen2.5-3B	xGen-small 4B Base
General Knowledge & Reasoning	ARC-Challenge	50.7	57.9	55.5	57.3
General Knowledge & Reasoning	Big-Bench Hard	39.1	40.6	46.1	50.9
General Knowledge & Reasoning	HellaSwag	76.3	77.6	74.6	78.5
General Knowledge & Reasoning	MMLU	56.1	59.5	65.6	62.6
General Knowledge & Reasoning	MMLU-Pro	25.1	28.1	32.0	31.8
General Knowledge & Reasoning	TruthfulQA	39.3	39.8	48.9	42.8
General Knowledge & Reasoning	WinoGrande	71.6	72.3	70.0	72.7
Math & Science	GPQA	28.3	29.3	29.3	29.4
Math & Science	GSM8K	28.0	40.6	59.1	71.9
Math & Science	MATH	9.0	25.2	40.7	43.1
Coding	HumanEval	28.1	34.6	38.3	42.5
Coding	HumanEval+	25.6	28.3	33.9	37.3
Coding	MBPP	33.2	42.2	42.0	45.0
Coding	MBPP+	38.5	52.4	52.0	54.0

Citation

@misc{xgensmall,
      title={xGen-small Technical Report}, 
      author={Erik Nijkamp and Bo Pang and Egor Pakhomov and Akash Gokul and Jin Qu and Silvio Savarese and Yingbo Zhou and Caiming Xiong},
      year={2025},
      eprint={2505.06496},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.06496}, 
}

Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people's lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.