Up to 3.2x Faster Inference with LFM2.5-DSpark
• 45
AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
View all activity
Articles
Update README.md
#1 opened about 21 hours ago
by 
iamleonie
Update README.md
#1 opened about 21 hours ago
by iamleonie
<|tool_call_start|> and <|tool_call_end|> The biggest problem with this model.
2
#18 opened 1 day ago
by 
koloved
Post
3765
Deploy local agents everywhere with LiquidAI/LFM2.5-2.6B
Unlike agents that depend on cloud APIs, local agents give you free inference, low latency, and real privacy.
Removing the per-token cost changes how developers build: agents can now be massively parallelized on local hardware, running background tasks that burn through millions of tokens at no marginal cost!
Unlike agents that depend on cloud APIs, local agents give you free inference, low latency, and real privacy.
Removing the per-token cost changes how developers build: agents can now be massively parallelized on local hardware, running background tasks that burn through millions of tokens at no marginal cost!
- 7 replies
Post
4896
Big update to llm-datasets, my curated list of datasets and tools for post-training LLMs.
> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.
Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.
Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
- 2 replies
mlabonne
authored 2
papers 7 months ago
Post
10558
New family of 1B models just dropped!
> LiquidAI/LFM2.5-1.2B-Base: 10T → 28T tokens
> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL
> LiquidAI/LFM2.5-1.2B-JP: our most polite model
> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual
> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality loss
Super proud of this release 🤗
> LiquidAI/LFM2.5-1.2B-Base: 10T → 28T tokens
> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL
> LiquidAI/LFM2.5-1.2B-JP: our most polite model
> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual
> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality loss
Super proud of this release 🤗
- 3 replies
ykhrustalev
authored a
paper 8 months ago
adityatadimeti
authored a
paper 9 months ago
fernandofernandes
authored 3
papers 9 months ago
Spectrum: Targeted Training on Signal to Noise Ratio
Paper • 2406.06623 • Published • 16
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 • 3
zetianli
authored a
paper 9 months ago
fernandofernandes
authored a
paper 9 months ago
kohsei
authored a
paper 9 months ago
GAD-cell
authored a
paper 11 months ago
Post
8515
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
CalderKat
authored a
paper 11 months ago
s-jse
authored a
paper 11 months ago