Slashing torch.compile Warmup & LoRA Swapping Times with Pruna
•
5
AI & ML interests
Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.
Recent Activity
View all activity
Articles
davidberenstein1957
published
a
dataset
about 10 hours ago
Article
Slashing torch.compile Warmup & LoRA Swapping Times with Pruna
•
5
davidberenstein1957
updated
a
collection
29 days ago
davidberenstein1957
published
an
article
29 days ago
Article
SmolLM-Smashed: Tiny Giants, Optimized for Speed
•
14
davidberenstein1957
posted
an
update
about 2 months ago
Post
2532
🚨 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
davidberenstein1957
updated
a
Space
3 months ago
Article
AI Model Optimization More Flexible Than Ever
•
13
Article
Effective Prompting for Generative Vision Models
•
9
johnrachwanpruna
updated
a
model
3 months ago
davidberenstein1957
published
a
dataset
4 months ago
johnrachwanpruna
updated
2
models
5 months ago
davidberenstein1957
posted
an
update
7 months ago
Post
613
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
davidberenstein1957
posted
an
update
7 months ago
Post
407
🚨 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
davidberenstein1957
posted
an
update
8 months ago
Post
1768
I created a collection of FLUX.1 models but 4x faster
PrunaAI/flux1-but-4x-faster-66c0b7340836dd7a55e9c0ea