tiiuae/Falcon-E-3B-Instruct

Table of Contents

0. TL;DR
1. Model Details
2. Training Details
3. Usage
4. Evaluation
5. Citation

TL;DR

Model Details

Model Description

• Developed by: https://www.tii.ae
• Model type: Causal decoder-only / Base version
• Architecture: Pure-transformer - 1.58bit version
• Language(s) (NLP): English
• License: Falcon-LLM License

Training details

For more details about the training protocol of this model, please refer to the Falcon-E technical blogpost.

Usage

Currently to use this model you can either rely on Hugging Face transformers library or BitNet library. There are multiple ways to interact with the model depending on your target usage. For each of the Falcon-E series model, you have three variants: the BitNet model, the prequantized checkpoint for fine-tuning and the bfloat16 version of the BitNet model.

Inference

🤗 transformers

In case you want to perform inference on the BitNet checkpoint run:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tiiuae/Falcon-E-3B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.bfloat16,
).to("cuda")

# Perform text generation

If you want to rather use the classic bfloat16 version, you can run:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tiiuae/Falcon-E-3B-Instruct"
revision = "bfloat16"

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.bfloat16,
  revision=revision,
).to("cuda")

# Perform text generation

BitNet

git clone https://github.com/microsoft/BitNet && cd BitNet
pip install -r requirements.txt
python setup_env.py --hf-repo tiiuae/Falcon-E-3B-Instruct -q i2_s
python run_inference.py -m models/Falcon-E-3B-Instruct/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv

Fine-tuning

For fine-tuning the model, you should load the prequantized revision of the model and use the onebitllms Python package:

import torch

from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import SFTTrainer
+ from onebitllms import replace_linear_with_bitnet_linear, quantize_to_1bit

model_id = "tiiuae/Falcon-E-3B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, revision="prequantized")
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
+    revision="prequantized"
)
+ model = replace_linear_with_bitnet_linear(model)

trainer = SFTTrainer(
    model,
    ...
)

trainer.train()

+ quantize_to_1bit(output_directory)

Evaluation

We report in the following table our internal pipeline benchmarks:

Note evaluation results are normalized score from former Hugging Face leaderboard v2 tasks

For 1B scale models and below

Model	Nb Params	Mem Footprint	IFEVAL	Math-Hard	GPQA	MuSR	BBH	MMLU-Pro	Avg.
Qwen-2.5-0.5B	0.5B	1GB	16.27	3.93	0.0	2.08	6.95	10.06	6.55
SmolLM2-360M	0.36B	720MB	21.15	1.21	0.0	7.73	5.54	1.88	6.25
Qwen-2.5-1.5B	1.5B	3.1GB	26.74	9.14	16.66	5.27	20.61	4.7	13.85
Llama-3.2-1B	1.24B	2.47GB	14.78	1.21	4.37	2.56	2.26	0	4.2
SmolLM2-1.7B	1.7B	3.4GB	24.4	2.64	9.3	4.6	12.64	3.91	9.58
Falcon-3-1B-Base	1.5B	3GB	24.28	3.32	11.34	9.71	6.76	3.91	9.89
Hymba-1.5B-Base	1.5B	3GB	22.95	1.36	7.69	5.18	10.25	0.78	8.04
Falcon-E-1B-Base	1.8B	635MB	32.9	10.97	2.8	3.65	12.28	17.82	13.40

For 3B scale models

Model	Nb Params	Mem Footprint	IFEVAL	Math-Hard	GPQA	MuSR	BBH	MMLU-Pro	Avg.
Falcon-3-3B-Base	3B	6.46GB	15.74	11.78	21.58	6.27	18.09	6.26	15.74
Qwen2.5-3B	3B	6.17GB	26.9	14.8	24.3	11.76	24.48	6.38	18.1
Falcon-E-3B-Base	3B	955MB	36.67	13.45	8.67	4.14	19.83	27.16	18.32

Below are the results for instruction fine-tuned models:

For 1B scale models and below

Model	Nb Params	Mem Footprint	IFEVAL	Math-Hard	GPQA	MuSR	BBH	MMLU-Pro	Avg.
Qwen-2.5-0.5B-Instruct	500M	1GB	30.71	0	8.43	0.94	7.75	0	6.59
SmolLM2-360M-Instruct	360M	720MB	38.42	1.51	4.17	2.77	1.3	0.67	8.14
Qwen-2.5-1.5B-Instruct	1.5B	3.1GB	44.76	22.05	19.81	3.19	19.99	0.78	18.43
SmolLM2-1.7B	1.7B	3.4GB	53.68	5.82	10.92	4.1	11.71	0	15.02
Falcon-3-1B-Instruct	1.5B	3GB	55.57	6.34	12.96	10.56	9.32	2.24	16.16
Hymba-1.5B-Instruct	1.5B	3GB	60.09	2.72	4.59	1.05	11.56	5.515	14.19
Falcon-E-1B-Instruct	1.8B	635MB	54.35	9.12	16.5	2.51	19.42	9.64	18.59

For 3B scale models

Model	Nb Params	Mem Footprint	IFEVAL	Math-Hard	GPQA	MuSR	BBH	MMLU-Pro	Avg.
Falcon-3-3B-Instruct	3B	6.46GB	69.77	25	26.29	11.13	22.28	5.15	26.6
Qwen2.5-3B-Instruct	3B	6.17GB	64.75	36.78	25.8	7.57	25.05	3.02	27.16
Falcon-E-3B-Instruct	3B	955MB	60.97	15.3	23.59	2.12	26.45	7.45	22.64666667

Useful links

• View our release blogpost.
• Learn more about onebitllms library.
• Feel free to join our discord server if you have any questions or to interact with our researchers and developers.

Citation

If the Falcon-E family of models were helpful to your work, feel free to give us a cite.

@misc{tiionebitllms,
    title = {Falcon-E, a series of powerful, universal and fine-tunable 1.58bit language models.},
    author = {Falcon-LLM Team},
    month = {April},
    url = {https://falcon-lm.github.io/blog/falcon-edge},
    year = {2025}
}