pkghf/images
Updated
Prabhat Kumar Gupta
pkghf
AI & ML interests
LLM, AI Agents, NLP, Visual LM
Recent Activity
updated a model 6 days ago
pkghf/images published a model 6 days ago
pkghf/images updated a bucket 6 days ago
pkghf/imagesOrganizations
updated a
model 6 days ago
published a
model 6 days ago
updated a
bucket 6 days ago
published a
bucket 6 days ago
upvoted an article about 1 month ago
Article
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval
- +1
aamirshakir, tomaarsen, SeanLee97
• • 135 upvoted a collection about 1 month ago
upvoted an article about 1 month ago
Article
Train 400x faster Static Embedding Models with Sentence Transformers
tomaarsen
• • 233 upvoted a paper about 1 month ago
upvoted 3
articles about 1 month ago
Article
🪆 Introduction to Matryoshka Embedding Models
- +1
tomaarsen, Xenova, osanseviero
• • 210 Article
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 72 Article
Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 62 upvoted 2
articles about 2 months ago
Article
Training and Finetuning Sparse Embedding Models with Sentence Transformers
tomaarsen, arthurbresnu
• • 138 Article
Training and Finetuning Embedding Models with Sentence Transformers
tomaarsen
• • 275 upvoted 2
articles 4 months ago
Article
SetFit: Efficient Few-Shot Learning Without Prompts
- +4
Unso, lewtun, luketheduke, danielkorat, orenpereg, moshew
• • 41 Article
Mixture of Experts (MoEs) in Transformers
- +5
ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap
• • 169 commented on Assisted Generation: a new direction toward low-latency text generation 4 months ago
Great Blog. The accuracy is totally dependent on few factors like use of Greedy decoding and high quality of Assistant models.
Also the latency gains is significant with smaller assistant models which creates a tradeoff between its accuracy vs speed
upvoted 2
articles 4 months ago
Article
Assisted Generation: a new direction toward low-latency text generation
joaogante
• • 79 Article
We Got Claude to Build CUDA Kernels and teach open models!
- +2
burtenshaw, evalstate, merve, pcuenq
• • 158 updated a
dataset 7 months ago
published a
dataset 7 months ago