LFM2 Technical Report
Paper
•
2511.23404
•
Published
•
40
AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
View all activity
ykhrustalev
authored
a
paper
3 days ago
adityatadimeti
authored
a
paper
24 days ago
saxenan3
authored
5
papers
25 days ago
NeuralArTS: Structuring Neural Architecture Search with Type Theory
Paper
•
2110.08710
•
Published
Towards One Shot Search Space Poisoning in Neural Architecture Search
Paper
•
2111.07138
•
Published
Consent in Crisis: The Rapid Decline of the AI Data Commons
Paper
•
2407.14933
•
Published
•
14
Bridging the Data Provenance Gap Across Text, Speech and Video
Paper
•
2412.17847
•
Published
•
10
LFM2 Technical Report
Paper
•
2511.23404
•
Published
•
40
fernandofernandes
authored
3
papers
26 days ago
Spectrum: Targeted Training on Signal to Noise Ratio
Paper
•
2406.06623
•
Published
•
15
Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation
Paper
•
2406.14971
•
Published
Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
Paper
•
2506.06607
•
Published
•
2
zetianli
authored
a
paper
26 days ago
fernandofernandes
authored
a
paper
26 days ago
ArthurBook
authored
a
paper
26 days ago
kohsei
authored
a
paper
27 days ago
sam-paech
authored
3
papers
2 months ago
EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Paper
•
2312.06281
•
Published
•
2
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
Paper
•
2508.07485
•
Published
•
10
Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
Paper
•
2510.15061
•
Published
•
1
Post
7794
LiquidAI/LFM2-8B-A1B just dropped!
8.3B params with only 1.5B active/token 🚀
> Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B
> MoE designed to run on phones/laptops (llama.cpp / vLLM)
> Pre-trained on 12T tokens → strong math/code/IF
8.3B params with only 1.5B active/token 🚀
> Quality ≈ 3–4B dense, yet faster than Qwen3-1.7B
> MoE designed to run on phones/laptops (llama.cpp / vLLM)
> Pre-trained on 12T tokens → strong math/code/IF
- 1 reply
Post
3728
⚛️ New drop of tiny task-specific models!
Want to do data extraction, translation, RAG, tool use, or math on a Raspberry Pi? We got you covered! ✅
These tiny models were fine-tuned to perform narrow tasks extremely well, making them competitive with much larger models.
You can deploy them today on-device or even on GPUs for big data operations!
LiquidAI/liquid-nanos-68b98d898414dd94d4d5f99a
Want to do data extraction, translation, RAG, tool use, or math on a Raspberry Pi? We got you covered! ✅
These tiny models were fine-tuned to perform narrow tasks extremely well, making them competitive with much larger models.
You can deploy them today on-device or even on GPUs for big data operations!
LiquidAI/liquid-nanos-68b98d898414dd94d4d5f99a
- 1 reply
Post
6872
Liquid just released two 450M and 1.6B param VLMs!
They're super fast and leverage SigLIP2 NaFlex encoders to handle native resolutions without distortion. It's ideal for on-device deployment in constrained environments like phones.
It's available today on Hugging Face, with an inference and a fine-tuning Colab notebooks.
LiquidAI/LFM2-VL-450M
LiquidAI/LFM2-VL-1.6B
They're super fast and leverage SigLIP2 NaFlex encoders to handle native resolutions without distortion. It's ideal for on-device deployment in constrained environments like phones.
It's available today on Hugging Face, with an inference and a fine-tuning Colab notebooks.
LiquidAI/LFM2-VL-450M
LiquidAI/LFM2-VL-1.6B