Hugging Face's logo

open/ acc

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

fuzzy-mittenzย  new activity 4 days ago
open-acc/README:[open/acc ] for Business - Dark Thoughts -๐Ÿ˜ˆ
Tonicย  new activity 8 days ago
open-acc/README:[open/acc ] for Business - Dark Thoughts -๐Ÿ˜ˆ
mmhamdyย  authored a paper 16 days ago
Bridging the Data Provenance Gap Across Text, Speech and Video
View all activity

open-acc's activity

merveย 
posted an update 2 days ago
view post
Post
3327
there's a new multimodal retrieval model in town ๐Ÿค 
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM ๐Ÿ’จ
> shrinkable with matryoshka ๐Ÿช†
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual ๐Ÿ“–
fuzzy-mittenzย 
in open-acc/README 4 days ago

[open/acc ] for Business - Dark Thoughts -๐Ÿ˜ˆ

6
#8 opened about 2 months ago by
Tonic
merveย 
posted an update 5 days ago
view post
Post
3425
What a beginning to this year in open ML ๐Ÿค 
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714

Multimodal ๐Ÿ–ผ๏ธ
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook โ€” 22k hours worth of samples from instruction videos ๐Ÿคฏ
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!

LLMs ๐Ÿ’ฌ
> Microsoft released Phi-4, sota open-source 14B language model ๐Ÿ”ฅ
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B ๐Ÿฌ๐Ÿฌ
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct ๐Ÿ’ญ
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview ๐Ÿ“•
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs ๐Ÿ“•
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences ๐Ÿ‘ฉ๐Ÿปโ€๐Ÿ’ป

Embeddings ๐Ÿ”–
> @MoritzLaurer released zero-shot version of ModernBERT large ๐Ÿ‘
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B

Image/Video Generation โฏ๏ธ
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts ๐Ÿ”ฅ
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M

Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding
Sri-Vigneshwar-DJย 
posted an update 6 days ago
view post
Post
592
Checkout phi-4 from Microsoft, dropped a day ago... If you โค๏ธ the Phi series, then here is the GGUF - Sri-Vigneshwar-DJ/phi-4-GGUF. phi-4 is a 14B highly efficient open LLM that beats much larger models at math and reasoning - check out evaluations on the Open LLM.

Technical paper - https://arxiv.org/pdf/2412.08905 ; The Data Synthesis approach is interesting
cfahlgren1ย 
posted an update 6 days ago
view post
Post
1299
Wow, I just added Langfuse tracing to the Deepseek Artifacts app and it's really nice ๐Ÿ”ฅ

It allows me to visualize and track more things along with the cfahlgren1/react-code-instructions dataset.

It was just added as a one click Docker Space template, so it's super easy to self host ๐Ÿ’ช
BrigitteTousiย 
posted an update 6 days ago
view post
Post
935
Community fine-tuned models are more carbon efficient than the models they are derived from! ๐Ÿฅณ๐ŸŒฟ

@alozowski @clefourrier @SaylorTwift @albertvillanova evaluated COโ‚‚ emissions associated with model inference for over 3000 models on the Open LLM Leaderboard. Interesting trends and new insights emerged...๐Ÿ‘€

Blog Post: https://huggingface.co/blog/leaderboard-emissions-analysis

Leaderboard: open-llm-leaderboard/open_llm_leaderboard
merveย 
posted an update 6 days ago
view post
Post
1719
ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license ๐Ÿ’— ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093

> The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos โฏ๏ธ

> The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint)

> The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM ๐Ÿ’ฌ

the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks โคต๏ธ

> Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.
  • 1 reply
ยท
mitkoxย 
posted an update 7 days ago
view post
Post
2361
Can it run DeepSeek V3 671B is the new 'can it run Doom'.

How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.

Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
ยท
Tonicย 
in open-acc/README 8 days ago

[open/acc ] for Business - Dark Thoughts -๐Ÿ˜ˆ

6
#8 opened about 2 months ago by
Tonic
andrewrreedย 
posted an update 8 days ago
view post
Post
2582
๐Ÿš€ Supercharge your LLM apps with Langfuse on Hugging Face Spaces!

Langfuse brings end-to-end observability and tooling to accelerate your dev workflow from experiments through production

Now available as a Docker Space directly on the HF Hub! ๐Ÿค—

๐Ÿ” Trace everything: monitor LLM calls, retrieval, and agent actions with popular frameworks
1โƒฃ One-click deployment: on Spaces with persistent storage and integrated OAuth
๐Ÿ›  Simple Prompt Management: Version, edit, and update without redeployment
โœ… Intuitive Evals: Collect user feedback, run model/prompt evaluations, and improve quality
๐Ÿ“Š Dataset Creation: Build datasets directly from production data to enhance future performance

Kudos to the Langfuse team for this collab and the awesome, open-first product theyโ€™re building! ๐Ÿ‘ @marcklingen @Clemo @MJannik

๐Ÿ”— Space: langfuse/langfuse-template-space
๐Ÿ”— Docs: https://huggingface.co/docs/hub/spaces-sdks-docker-langfuse
  • 1 reply
ยท
jeffboudierย 
posted an update 8 days ago
view post
Post
504
NVIDIA just announced the Cosmos World Foundation Models, available on the Hub: nvidia/cosmos-6751e884dc10e013a0a0d8e6

Cosmos is a family of pre-trained models purpose-built for generating physics-aware videos and world states to advance physical AI development.
The release includes Tokenizers nvidia/cosmos-tokenizer-672b93023add81b66a8ff8e6

Learn more in this great community article by @mingyuliutw and @PranjaliJoshi https://huggingface.co/blog/mingyuliutw/nvidia-cosmos
  • 1 reply
ยท
Sri-Vigneshwar-DJย 
posted an update 9 days ago
view post
Post
2026
Just sharing a thought: I started using DeepSeek V3 a lot, and an idea struck me about agents "orchestrating during inference" on a test-time compute model like DeepSeek V3 or the O1 series.

Agents (Instruction + Function Calls + Memory) execute during inference, and based on the output decision, a decision is made to scale the time to reason or perform other tasks.
Sri-Vigneshwar-DJย 
posted an update 11 days ago
view post
Post
2323
Combining smolagents with Anthropicโ€™s best practices simplifies building powerful AI agents:

1. Code-Based Agents: Write actions as Python code, reducing steps by 30%.
2. Prompt Chaining: Break tasks into sequential subtasks with validation gates.
3. Routing: Classify inputs and direct them to specialized handlers.
4. Fallback: Handle tasks even if classification fails.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/building-effective-agents-with-anthropics-best-pra
cfahlgren1ย 
posted an update 12 days ago
view post
Post
2009
You'll notice the AI in the SQL Console is much better at working with chatml conversations:

Here's example of unnesting the cfahlgren1/react-code-instructions in less than 10 seconds by asking it. Check it out here: cfahlgren1/react-code-instructions

- "show me the average assistant response length"
- "extract user, system, and assistant messages into separate columns"

It's super easy to work with conversational datasets now with natural language ๐Ÿ—ฃ๏ธ
1aurentย 
posted an update 15 days ago
merveย 
posted an update 15 days ago
view post
Post
4748
supercharge your LLM apps with smolagents ๐Ÿ”ฅ

however cool your LLM is, without being agentic it can only go so far

enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!

Here's our blog for you to get started https://huggingface.co/blog/smolagents
mmhamdyย 
authored a paper 16 days ago
cfahlgren1ย 
posted an update 16 days ago
suayptalhaย 
posted an update 18 days ago
view post
Post
1845
๐Ÿš€ Introducing ๐…๐ข๐ซ๐ฌ๐ญ ๐‡๐ฎ๐ ๐ ๐ข๐ง๐  ๐…๐š๐œ๐ž ๐ˆ๐ง๐ญ๐ž๐ ๐ซ๐š๐ญ๐ข๐จ๐ง ๐จ๐Ÿ ๐ฆ๐ข๐ง๐†๐‘๐” ๐Œ๐จ๐๐ž๐ฅ๐ฌ from the paper ๐–๐ž๐ซ๐ž ๐‘๐๐๐ฌ ๐€๐ฅ๐ฅ ๐–๐ž ๐๐ž๐ž๐๐ž๐?

๐Ÿ–ฅ I have integrated ๐ง๐ž๐ฑ๐ญ-๐ ๐ž๐ง๐ž๐ซ๐š๐ญ๐ข๐จ๐ง ๐‘๐๐๐ฌ, specifically minGRU, which offer faster performance compared to Transformer architectures, into HuggingFace. This allows users to leverage the lighter and more efficient minGRU models with the "๐ญ๐ซ๐š๐ง๐ฌ๐Ÿ๐จ๐ซ๐ฆ๐ž๐ซ๐ฌ" ๐ฅ๐ข๐›๐ซ๐š๐ซ๐ฒ for both usage and training.

๐Ÿ’ป I integrated two main tasks: ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง and ๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐‚๐š๐ฎ๐ฌ๐š๐ฅ๐‹๐Œ.

๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง:
You can use this class for ๐’๐ž๐ช๐ฎ๐ž๐ง๐œ๐ž ๐‚๐ฅ๐š๐ฌ๐ฌ๐ข๐Ÿ๐ข๐œ๐š๐ญ๐ข๐จ๐ง tasks. I also trained a Sentiment Analysis model with stanfordnlp/imdb dataset.

๐Œ๐ข๐ง๐†๐‘๐”๐…๐จ๐ซ๐‚๐š๐ฎ๐ฌ๐š๐ฅ๐‹๐Œ:
You can use this class for ๐‚๐š๐ฎ๐ฌ๐š๐ฅ ๐‹๐š๐ง๐ ๐ฎ๐š๐ ๐ž ๐Œ๐จ๐๐ž๐ฅ tasks such as GPT, Llama. I also trained an example model with roneneldan/TinyStories dataset. You can fine-tune and use it!

๐Ÿ”— ๐‹๐ข๐ง๐ค๐ฌ:
Models: suayptalha/mingru-676fe8d90760d01b7955d7ab
GitHub: https://github.com/suayptalha/minGRU-hf
LinkedIn Post: https://www.linkedin.com/posts/suayp-talha-kocabay_mingru-a-suayptalha-collection-activity-7278755484172439552-wNY1

๐Ÿ“ฐ ๐‚๐ซ๐ž๐๐ข๐ญ๐ฌ:
Paper Link: https://arxiv.org/abs/2410.01201

I am thankful to Leo Feng, Frederick Tung, Mohamed Osama Ahmed, Yoshua Bengio and Hossein Hajimirsadeghi for their papers.
suayptalhaย 
posted an update 21 days ago
view post
Post
2459
๐Ÿš€ Introducing Substitution Cipher Solvers!

As @suayptalha and @Synd209 we are thrilled to share an update!

๐Ÿ”‘ This project contains a text-to-text model designed to decrypt English and Turkish text encoded using a substitution cipher. In a substitution cipher, each letter in the plaintext is replaced by a corresponding, unique letter to form the ciphertext. The model leverages statistical and linguistic properties of English to make educated guesses about the letter substitutions, aiming to recover the original plaintext message.

These models were fine-tuned on T5-base. The models are for monoalphabetic English and Turkish substitution ciphers, and they output decoded text and the alphabet with an accuracy that has never been achieved before!

Example:

Encoded text: Z hztwgx tstcsf qf z ulooqfe osfuqb tzx uezx awej z ozewsbe vlfwby fsmqisfx.

Decoded text: A family member or a support person may stay with a patient during recovery.

Model Collection Link: Cipher-AI/substitution-cipher-solvers-6731ebd22f0f0d8e0e2e2e00

Organization Link: https://huggingface.co/Cipher-AI
  • 3 replies
ยท