SmolLM-Smashed: Tiny Giants, Optimized for Speed
β’
3
AI & ML interests
Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.
Recent Activity
Articles
davidberenstein1957Β
updated
a
collection
about 6 hours ago
davidberenstein1957Β
published
an
article
about 6 hours ago
Article
SmolLM-Smashed: Tiny Giants, Optimized for Speed
β’
3
davidberenstein1957Β
posted
an
update
28 days ago
Post
2463
π¨ Phare LLM benchmark V2: Reasoning models don't guarantee better security
Read the full blog here: https://huggingface.co/blog/davidberenstein1957/phare-llm-benchmark-v2
Read the full blog here: https://huggingface.co/blog/davidberenstein1957/phare-llm-benchmark-v2
davidberenstein1957Β
updated
a
Space
about 2 months ago
Article
AI Model Optimization More Flexible Than Ever
β’
13
Article
Effective Prompting for Generative Vision Models
β’
9
johnrachwanprunaΒ
updated
a
model
2 months ago
davidberenstein1957Β
published
a
dataset
3 months ago
johnrachwanprunaΒ
updated
2
models
4 months ago
davidberenstein1957Β
posted
an
update
6 months ago
Post
607
Announcing RealPerformance, a dataset of functional issues of language models that mirrors failure patterns identified through rigorous testing in real LLM agents
https://huggingface.co/blog/davidberenstein1957/realperformance-llm-business-compliance
https://huggingface.co/blog/davidberenstein1957/realperformance-llm-business-compliance
davidberenstein1957Β
posted
an
update
6 months ago
Post
402
π¨ LLMs recognise bias but also reproduce harmful stereotypes: an analysis of bias in leading LLMs
I've written a new entry in our series on the Giskard, BPIFrance and Google Deepmind Phare benchmark(phare.giskard.ai).
This time it covers bias: https://huggingface.co/blog/davidberenstein1957/llms-recognise-bias-but-also-produce-stereotypes
Previous entry on hallucinations: https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms
I've written a new entry in our series on the Giskard, BPIFrance and Google Deepmind Phare benchmark(phare.giskard.ai).
This time it covers bias: https://huggingface.co/blog/davidberenstein1957/llms-recognise-bias-but-also-produce-stereotypes
Previous entry on hallucinations: https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms
- 1 reply
davidberenstein1957Β
posted
an
update
7 months ago
Post
1766
I created a collection of FLUX.1 models but 4x faster
PrunaAI/flux1-but-4x-faster-66c0b7340836dd7a55e9c0ea
davidberenstein1957Β
posted
an
update
8 months ago
Post
1096
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs
https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms
https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms
Post
3193
How to learn about efficient AI? - Happy to announce the Awesome AI Efficiency repo that gathers a curated list of 100+ materials to understand the challenges and solutions in making AI faster, smaller, cheaper, greener.
π It is designed for a **large audience** including beginners, decision-makers, engineers, and researchers.
π It contains **diverse materials** with newspaper articles, blogs, tools, tech reports, research papers, books, and lectures.
This is an ongoing project. Do not hesitate to share your feedback/suggestions and star the repo! π
https://github.com/PrunaAI/awesome-ai-efficiency
π It is designed for a **large audience** including beginners, decision-makers, engineers, and researchers.
π It contains **diverse materials** with newspaper articles, blogs, tools, tech reports, research papers, books, and lectures.
This is an ongoing project. Do not hesitate to share your feedback/suggestions and star the repo! π
https://github.com/PrunaAI/awesome-ai-efficiency
- 2 replies