44
Face Swap PRO
๐ป
Give you the best results.
Denys
JoniJOST
AI & ML interests
None yet
Recent Activity
liked
a Space
13 days ago
ovi054/face-swap-pro
liked
a Space
13 days ago
FaceOnLive/Face-Search-Online
upvoted
a
paper
13 days ago
DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian
Splat Generation
Organizations
None yet
JoniJOST's activity
liked
2
Spaces
13 days ago
upvoted
a
paper
13 days ago
reacted to
m-ric's
post with ๐ฅ
13 days ago
Post
3904
๐ง๐ต๐ฒ ๐๐๐ฏ ๐๐ฒ๐น๐ฐ๐ผ๐บ๐ฒ๐ ๐ฒ๐
๐๐ฒ๐ฟ๐ป๐ฎ๐น ๐ถ๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ ๐ฝ๐ฟ๐ผ๐๐ถ๐ฑ๐ฒ๐ฟ๐!
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
- 1 reply
reacted to
cfahlgren1's
post with ๐ค
13 days ago
Post
1906
If you haven't seen yet, we just released Inference Providers ๐
> 4 new serverless inference providers on the Hub ๐คฏ
> Use your HF API key or personal key with all providers ๐
> Chat with Deepseek R1, V3, and more on HF Hub ๐
> We support Sambanova, TogetherAI, Replicate, and Fal.ai ๐ช
Best of all, we don't charge any markup on top of the provider ๐ซฐ Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
> 4 new serverless inference providers on the Hub ๐คฏ
> Use your HF API key or personal key with all providers ๐
> Chat with Deepseek R1, V3, and more on HF Hub ๐
> We support Sambanova, TogetherAI, Replicate, and Fal.ai ๐ช
Best of all, we don't charge any markup on top of the provider ๐ซฐ Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
reacted to
dylanebert's
post with ๐ค
13 days ago
Post
3030
I made a 1 minute video explaining the DeepSeek situation
R1: deepseek-ai/DeepSeek-R1
Janus Pro: deepseek-ai/Janus-Pro-7B
R1: deepseek-ai/DeepSeek-R1
Janus Pro: deepseek-ai/Janus-Pro-7B
- 3 replies
reacted to
prithivMLmods's
post with ๐ค
13 days ago
Post
5099
Deepswipe by
.
.
.
. Deepseek๐ฌ๐ฟ
Everything is now in recovery. ๐๐
.
.
.
. Deepseek๐ฌ๐ฟ
Everything is now in recovery. ๐๐
- 4 replies
reacted to
singhsidhukuldeep's
post with ๐ค
13 days ago
Post
1663
Groundbreaking Research Alert: Can Large Language Models Really Understand Personal Preferences?
A fascinating new study from researchers at University of Notre Dame, Xi'an Jiaotong University, and Universitรฉ de Montrรฉal introduces PERRECBENCH - a novel benchmark for evaluating how well Large Language Models (LLMs) understand user preferences in recommendation systems.
Key Technical Insights:
- The benchmark eliminates user rating bias and item quality factors by using relative ratings and grouped ranking approaches
- Implements three distinct ranking methods: pointwise rating prediction, pairwise comparison, and listwise ranking
- Evaluates 19 state-of-the-art LLMs including Claude-3.5, GPT-4, Llama-3, Mistral, and Qwen models
- Uses Kendall's tau correlation to measure ranking accuracy
- Incorporates BM25 retriever with configurable history items (k=4 by default)
Notable Findings:
- Current LLMs struggle with true personalization, achieving only moderate correlation scores
- Larger models don't always perform better - challenging conventional scaling laws
- Pairwise and listwise ranking methods outperform pointwise approaches
- Open-source models like Mistral-123B and Llama-3-405B compete well with proprietary models
- Weight merging strategy shows promise for improving personalization capabilities
The research reveals that while LLMs excel at many tasks, they still face significant challenges in understanding individual user preferences. This work opens new avenues for improving personalized recommendation systems and highlights the importance of developing better evaluation methods.
A must-read for anyone interested in LLMs, recommender systems, or personalization technology. The team has made their benchmark and code publicly available for further research.
A fascinating new study from researchers at University of Notre Dame, Xi'an Jiaotong University, and Universitรฉ de Montrรฉal introduces PERRECBENCH - a novel benchmark for evaluating how well Large Language Models (LLMs) understand user preferences in recommendation systems.
Key Technical Insights:
- The benchmark eliminates user rating bias and item quality factors by using relative ratings and grouped ranking approaches
- Implements three distinct ranking methods: pointwise rating prediction, pairwise comparison, and listwise ranking
- Evaluates 19 state-of-the-art LLMs including Claude-3.5, GPT-4, Llama-3, Mistral, and Qwen models
- Uses Kendall's tau correlation to measure ranking accuracy
- Incorporates BM25 retriever with configurable history items (k=4 by default)
Notable Findings:
- Current LLMs struggle with true personalization, achieving only moderate correlation scores
- Larger models don't always perform better - challenging conventional scaling laws
- Pairwise and listwise ranking methods outperform pointwise approaches
- Open-source models like Mistral-123B and Llama-3-405B compete well with proprietary models
- Weight merging strategy shows promise for improving personalization capabilities
The research reveals that while LLMs excel at many tasks, they still face significant challenges in understanding individual user preferences. This work opens new avenues for improving personalized recommendation systems and highlights the importance of developing better evaluation methods.
A must-read for anyone interested in LLMs, recommender systems, or personalization technology. The team has made their benchmark and code publicly available for further research.
reacted to
mkurman's
post with ๐ค
13 days ago
Post
2755
Ok, my 14B DeepSeek R1 merge with Qwen2.5 1M is really hot right nowโit's got 2.6k downloads! It's sitting pretty as the top trending model on the third page. ๐ฅ
Check it out if you haven't already!
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
Check it out if you haven't already!
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
- 11 replies
reacted to
csabakecskemeti's
post with ๐ค
13 days ago
Post
2058
I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.
Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.
Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF
-
- 6 replies