helium-1-preview-2b

Model Details

Model Description

Helium-1 preview is a lightweight language model with 2B parameters, targeting edge and mobile devices. It supports the following languages: English, French, German, Italian, Portuguese, Spanish.

⚠️ Helium-1 Preview is a base model, which was not fine-tuned to follow instructions or human preferences. For most downstream use cases, the model should be aligned with supervised fine-tuning, RLHF or related methods.

Developed by: Kyutai
Model type: Large Language Model
Language(s) (NLP): English, French, German, Italian, Portuguese, Spanish
License: CC-BY 4.0

Uses

Direct Use

The intended use of the Helium model is research and development of natural language processing systems, including but not limited to language generation and understanding. The model can be used in English, French, German, Italian, Portuguese and Spanish. For most downstream use cases, the model should be aligned with supervised fine-tuning, RLHF or related methods.

Out-of-Scope Use

The model should not be used in other languages than the ones on which it was trained. The model is not intended to be used for any malicious or illegal activities of any kind. The model was not fine-tuned to follow instructions, and thus should not be used as such.

Bias, Risks, and Limitations

Helium-1 preview is a base language model, which was not aligned to human preferences. As such, the model can generate incorrect, biased, harmful or generally unhelpful content. Thus, the model should not be used for downstream applications without further alignment, evaluations and mitigations of risks.

How to Get Started with the Model

Use the code below to get started with the model.

import torch
from transformers import pipeline

model_id = "kyutai/helium-1-preview-2b"

pipe = pipeline(
    "text-generation", 
    model=model_id, 
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

text = pipe("Hello, today is a great day to")

Training Details

Training Data

Helium-1 preview was trained on a mix of data including: Wikipedia, Stack Exchange, open-access scientific articles (from peS2o) and Common Crawl.

Evaluation

Testing Data

The model was evaluated on MMLU, TriviaQA, NaturalQuestions, ARC Easy & Challenge, Open Book QA, Common Sense QA, Physical Interaction QA, Social Interaction QA, HellaSwag, WinoGrande, Multilingual Knowledge QA, FLORES 200.

Metrics

We report accuracy on MMLU, ARC, OBQA, CSQA, PIQA, SIQA, HellaSwag, WinoGrande. We report exact match on TriviaQA, NQ and MKQA. We report BLEU on FLORES.

English Results

Benchmark	Helium-1 Preview	HF SmolLM2 (1.7B)	Gemma-2 (2.6B)	Llama-3.2 (3B)	Qwen2.5 (1.5B)

MMLU	51.2	50.4	53.1	56.6	61.0
NQ	17.3	15.1	17.7	22.0	13.1
TQA	47.9	45.4	49.9	53.6	35.9
ARC E	80.9	81.8	81.1	84.6	89.7
ARC C	62.7	64.7	66.0	69.0	77.2
OBQA	63.8	61.4	64.6	68.4	73.8
CSQA	65.6	59.0	64.4	65.4	72.4
PIQA	77.4	77.7	79.8	78.9	76.0
SIQA	64.4	57.5	61.9	63.8	68.7
HS	69.7	73.2	74.7	76.9	67.5
WG	66.5	65.6	71.2	72.0	64.8

Average	60.7	59.3	62.2	64.7	63.6

Multilingual Results

Language	Benchmark	Helium-1 Preview	HF SmolLM2 (1.7B)	Gemma-2 (2.6B)	Llama-3.2 (3B)	Qwen2.5 (1.5B)

German	MMLU	45.6	35.3	45.0	47.5	49.5
	ARC C	56.7	38.4	54.7	58.3	60.2
	HS	53.5	33.9	53.4	53.7	42.8
	MKQA	16.1	7.1	18.9	20.2	10.4
	FLORES	33.9	12.2	30.7	28.2	20.8
Spanish	MMLU	46.5	38.9	46.2	49.6	52.8
	ARC C	58.3	43.2	58.8	60.0	68.1
	HS	58.6	40.8	60.5	61.1	51.4
	MKQA	16.0	7.9	18.5	20.6	10.6
	FLORES	25.7	15.0	25.7	23.7	20.4
French	MMLU	46.0	37.7	45.7	48.8	51.9
	ARC C	57.9	40.6	57.5	60.1	67.4
	HS	59.0	41.1	60.4	59.6	51.2
	MKQA	16.8	8.4	18.4	19.6	9.7
	FLORES	44.3	20.0	43.3	39.3	31.2
Italian	MMLU	46.1	36.3	45.6	48.8	50.5
	ARC C	57.4	39.1	53.9	60.1	64.6
	HS	55.2	37.7	56.2	56.8	46.8
	MKQA	15.3	6.3	18.0	19.0	9.9
	FLORES	25.8	10.4	25.2	23.8	16.4
Portuguese	MMLU	46.2	37.7	45.6	49.2	53.0
	ARC C	56.8	40.6	57.0	62.1	66.6
	HS	57.3	41.0	58.7	59.1	50.9
	MKQA	14.7	6.6	16.9	19.1	9.2
	FLORES	43.0	20.0	43.6	40.5	33.0

	Average	42.1	27.8	42.3	43.6	40.0

Technical Specifications

Model Architecture and Objective

Hyperparameter	Value
Layers	24
Heads	20
Model dimension	2560
MLP dimension	7040
Context size	4096
Theta RoPE	100,000

Hardware

The model was trained on 128 NVIDIA H100 Tensor Core GPUs.

Software

The model was trained using Jax.

Citation

Blog post: https://kyutai.org/2025/01/13/helium.html

kyutai/helium-1-preview-2b

Model Card