Inference for PROs
β’
50
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
reacted to
davidberenstein1957's
post
with π₯
14 minutes ago
replied to
elliesleightholm's
post
about 1 hour ago
reacted to
elliesleightholm's
post
with π€
about 1 hour ago
Articles
Organizations
victor's activity
reacted to
davidberenstein1957's
post with π₯
14 minutes ago
Post
89
π€π Introducing Observers: A Lightweight SDK for AI Observability ππ€
Observers is an open-source Python SDK that provides comprehensive observability for AI applications. Our library makes it easy to:
- Track and record interactions with AI models
- Store observations in multiple backends
- Query and analyse your AI interactions with ease
https://huggingface.co/blog/davidberenstein1957/observers-a-lightweight-sdk-for-ai-observability
Observers is an open-source Python SDK that provides comprehensive observability for AI applications. Our library makes it easy to:
- Track and record interactions with AI models
- Store observations in multiple backends
- Query and analyse your AI interactions with ease
https://huggingface.co/blog/davidberenstein1957/observers-a-lightweight-sdk-for-ai-observability
replied to
elliesleightholm's
post
about 1 hour ago
Great content! Marqo looks great π€
reacted to
elliesleightholm's
post with π€
about 1 hour ago
Post
97
I made a beginners guide to Hugging Face Spaces π€ I hope it's useful to some of you :)
YouTube video: https://www.youtube.com/watch?v=xqdTFyRdtjQ
Blog: https://www.marqo.ai/blog/how-to-create-a-hugging-face-space
YouTube video: https://www.youtube.com/watch?v=xqdTFyRdtjQ
Blog: https://www.marqo.ai/blog/how-to-create-a-hugging-face-space
-
- 2 replies
reacted to
cfahlgren1's
post with β€οΈ
about 14 hours ago
Post
2030
You can clean and format datasets entirely in the browser with a few lines of SQL.
In this post, I replicate the process @mlabonne used to clean the new microsoft/orca-agentinstruct-1M-v1 dataset.
The cleaning process consists of:
- Joining the separate splits together / add split column
- Converting string messages into list of structs
- Removing empty system prompts
https://huggingface.co/blog/cfahlgren1/the-beginners-guide-to-cleaning-a-dataset
Here's his new cleaned dataset: mlabonne/orca-agentinstruct-1M-v1-cleaned
In this post, I replicate the process @mlabonne used to clean the new microsoft/orca-agentinstruct-1M-v1 dataset.
The cleaning process consists of:
- Joining the separate splits together / add split column
- Converting string messages into list of structs
- Removing empty system prompts
https://huggingface.co/blog/cfahlgren1/the-beginners-guide-to-cleaning-a-dataset
Here's his new cleaned dataset: mlabonne/orca-agentinstruct-1M-v1-cleaned
- 1 reply
reacted to
jsulz's
post with π₯
about 15 hours ago
Post
779
When the XetHub crew joined Hugging Face this fall,
@erinys
and I started brainstorming how to share our work to replace Git LFS on the Hub. Uploading and downloading large models and datasets takes precious time. Thatβs where our chunk-based approach comes in.
Instead of versioning files (like Git and Git LFS), we version variable-sized chunks of data. For the Hugging Face community, this means:
β© Only upload the chunks that changed.
π Download just the updates, not the whole file.
π§ We store your file as deduplicated chunks
In our benchmarks, we found that using CDC to store iterative model and dataset version led to transfer speedups of ~2x, but this isnβt just a performance boost. Itβs a rethinking of how we manage models and datasets on the Hub.
We're planning on our new storage backend to the Hub in early 2025 - check out our blog to dive deeper, and let us know: how could this improve your workflows?
https://huggingface.co/blog/from-files-to-chunks
Instead of versioning files (like Git and Git LFS), we version variable-sized chunks of data. For the Hugging Face community, this means:
β© Only upload the chunks that changed.
π Download just the updates, not the whole file.
π§ We store your file as deduplicated chunks
In our benchmarks, we found that using CDC to store iterative model and dataset version led to transfer speedups of ~2x, but this isnβt just a performance boost. Itβs a rethinking of how we manage models and datasets on the Hub.
We're planning on our new storage backend to the Hub in early 2025 - check out our blog to dive deeper, and let us know: how could this improve your workflows?
https://huggingface.co/blog/from-files-to-chunks
replied to
LukeNeumann's
post
about 22 hours ago
Not me but yes I think the community would do something with it.
reacted to
monsoon-nlp's
post with β€οΈ
about 22 hours ago
Post
992
Great to see Tatta Bio release an embeddings version of their DNA/protein language model π§¬:
tattabio/gLM2_650M_embed
reacted to
AkimfromParis's
post with π
about 22 hours ago
Post
799
π―π΅ The Open Japanese LLM Leaderboard created by LLM-jp πΈ in partnership with HuggingFace π€ was released today!
Blog: https://huggingface.co/blog/leaderboard-japanese
Space: llm-jp/open-japanese-llm-leaderboard
π The leaderboard is available in both Japanese and English
π Based on the evaluation tool, llm-jp-eval with more than 20 datasets for Japanese LLMs
π The leaderboard showcases all the metrics for NLP experts, plus averages for NLP beginners
π» For the comfort of users, we chose a horizontal UI, and implemented it in a light and dark theme on Gradio
π¬ The radar chart provides a very interesting visualization of metrics!
π± We are using the Japanese research platform, MDX, so please be patient!
β‘ LLM bigger than +70B will be evaluated soonβ¦
How do you say βGPUs Go Brrrβ in Japanese - > GPUγγγ³γγ³ο½! (To pronounce "GPU ga bunbun!") π₯
Blog: https://huggingface.co/blog/leaderboard-japanese
Space: llm-jp/open-japanese-llm-leaderboard
π The leaderboard is available in both Japanese and English
π Based on the evaluation tool, llm-jp-eval with more than 20 datasets for Japanese LLMs
π The leaderboard showcases all the metrics for NLP experts, plus averages for NLP beginners
π» For the comfort of users, we chose a horizontal UI, and implemented it in a light and dark theme on Gradio
π¬ The radar chart provides a very interesting visualization of metrics!
π± We are using the Japanese research platform, MDX, so please be patient!
β‘ LLM bigger than +70B will be evaluated soonβ¦
How do you say βGPUs Go Brrrβ in Japanese - > GPUγγγ³γγ³ο½! (To pronounce "GPU ga bunbun!") π₯
- 4 replies
replied to
LukeNeumann's
post
1 day ago
You're a legend! and yes the dataset would be π₯
reacted to
LukeNeumann's
post with π€―
1 day ago
Post
1005
Nine years ago, I uploaded the first 8K resolution video to YouTube and I've been stockpiling 8K footage ever since: https://www.youtube.com/watch?v=sLprVF6d7Ug&t
Should @Overlaiapp release the first open-source 8K video dataset?
Could anyone even fine tune a model with this?π
Should @Overlaiapp release the first open-source 8K video dataset?
Could anyone even fine tune a model with this?π
-
- 6 replies
reacted to
davidberenstein1957's
post with π₯
1 day ago
Post
1788
For anyone who struggles with NER or information extraction with LLM.
We showed an efficient workflow for token classification including zero-shot suggestions and model fine-tuning with Argilla, GliNER, the NuMind NuExtract LLM and SpanMarker. @argilla
Video: https://youtu.be/JvLpaYgNd84?feature=shared
Notebooks and slides included to try it yourself π
We showed an efficient workflow for token classification including zero-shot suggestions and model fine-tuning with Argilla, GliNER, the NuMind NuExtract LLM and SpanMarker. @argilla
Video: https://youtu.be/JvLpaYgNd84?feature=shared
Notebooks and slides included to try it yourself π
replied to
their
post
3 days ago
Thanks, we'll see what we can do about filtering model based on parameter size (imo no super clear way to do it well, we need to think about it a bit).
replied to
their
post
3 days ago
Something new is coming soon regarding all this π (stay tuned)
reacted to
bartowski's
post with β€οΈ
3 days ago
Post
15840
In regards to the latest mistral model and GGUFs for it:
Yes, they may be subpar and may require changes to llama.cpp to support the interleaved sliding window
Yes, I got excited when a conversion worked and released them ASAP
That said, generation seems to work right now and seems to mimic the output from spaces that are running the original model
I have appended -TEST to the model names in an attempt to indicate that they are not final or perfect, but if people still feel mislead and that it's not the right thing to do, please post (civilly) below your thoughts, I will highly consider pulling the conversions if that's what people think is best. After all, that's what I'm here for, in service to you all !
Yes, they may be subpar and may require changes to llama.cpp to support the interleaved sliding window
Yes, I got excited when a conversion worked and released them ASAP
That said, generation seems to work right now and seems to mimic the output from spaces that are running the original model
I have appended -TEST to the model names in an attempt to indicate that they are not final or perfect, but if people still feel mislead and that it's not the right thing to do, please post (civilly) below your thoughts, I will highly consider pulling the conversions if that's what people think is best. After all, that's what I'm here for, in service to you all !
- 6 replies
reacted to
hexgrad's
post with π₯
4 days ago
Post
3086
Kokoro: a small, fast 80M param TTS model hosted on ZeroGPU at
hexgrad/Kokoro-TTS
- 3 replies
reacted to
merve's
post with π₯
4 days ago
Post
4629
OmniVision-968M: a new local VLM for edge devices, fast & small but performant
π¨ a new vision language model with 9x less image tokens, super efficient
π aligned with DPO for reducing hallucinations
β‘οΈ Apache 2.0 license π₯
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M
π¨ a new vision language model with 9x less image tokens, super efficient
π aligned with DPO for reducing hallucinations
β‘οΈ Apache 2.0 license π₯
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M
- 4 replies
reacted to
prithivMLmods's
post with π€
4 days ago
Post
3830
Minimalistic Adapters π
πDemo Here:
prithivMLmods/FLUX-LoRA-DLC
πModel:
{ Quote Tuner } : prithivMLmods/Flux.1-Dev-Quote-LoRA
{ Stamp Art } : prithivMLmods/Flux.1-Dev-Stamp-Art-LoRA
{ Hand Sticky } : prithivMLmods/Flux.1-Dev-Hand-Sticky-LoRA
{ Poster HQ } : prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA
{ Ctoon Min } : prithivMLmods/Flux.1-Dev-Ctoon-LoRA
πCollection:
{ Flux LoRA Collection} : prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
{ LoRA Space Collection } : prithivMLmods/lora-space-collections-6714b72e0d49e1c97fbd6a32
πFor More Visit
https://huggingface.co/strangerzonehf
.
.
.
π€@prithivMLmods
πDemo Here:
prithivMLmods/FLUX-LoRA-DLC
πModel:
{ Quote Tuner } : prithivMLmods/Flux.1-Dev-Quote-LoRA
{ Stamp Art } : prithivMLmods/Flux.1-Dev-Stamp-Art-LoRA
{ Hand Sticky } : prithivMLmods/Flux.1-Dev-Hand-Sticky-LoRA
{ Poster HQ } : prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA
{ Ctoon Min } : prithivMLmods/Flux.1-Dev-Ctoon-LoRA
πCollection:
{ Flux LoRA Collection} : prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
{ LoRA Space Collection } : prithivMLmods/lora-space-collections-6714b72e0d49e1c97fbd6a32
πFor More Visit
https://huggingface.co/strangerzonehf
.
.
.
π€@prithivMLmods
- 3 replies
reacted to
reach-vb's
post with π
4 days ago
Post
3914
What a brilliant week for Open Source AI!
Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17%
microsoft/llm2clip-672323a266173cfa40b32d4c
Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents
Nexusflow/athene-v2-6735b85e505981a794fb02cc
Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed
microsoft/orca-agentinstruct-1M-v1
Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder
reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71
JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow
deepseek-ai/JanusFlow-1.3B
Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens!
PleIAs/common_corpus
I'm sure I missed a lot, can't wait for the next week!
Put down in comments what I missed! π€
Qwen 2.5 Coder by Alibaba - 0.5B / 1.5B / 3B / 7B / 14B/ 32B (Base + Instruct) Code generation LLMs, with 32B tackling giants like Gemnini 1.5 Pro, Claude Sonnet
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
LLM2CLIP from Microsoft - Leverage LLMs to train ultra-powerful CLIP models! Boosts performance over the previous SOTA by ~17%
microsoft/llm2clip-672323a266173cfa40b32d4c
Athene v2 Chat & Agent by NexusFlow - SoTA general LLM fine-tuned from Qwen 2.5 72B excels at Chat + Function Calling/ JSON/ Agents
Nexusflow/athene-v2-6735b85e505981a794fb02cc
Orca Agent Instruct by Microsoft - 1 million instruct pairs covering text editing, creative writing, coding, reading comprehension, etc - permissively licensed
microsoft/orca-agentinstruct-1M-v1
Ultravox by FixieAI - 70B/ 8B model approaching GPT4o level, pick any LLM, train an adapter with Whisper as Audio Encoder
reach-vb/ultravox-audio-language-model-release-67373b602af0a52b2a88ae71
JanusFlow 1.3 by DeepSeek - Next iteration of their Unified MultiModal LLM Janus with RectifiedFlow
deepseek-ai/JanusFlow-1.3B
Common Corpus by Pleais - 2,003,039,184,047 multilingual, commercially permissive and high quality tokens!
PleIAs/common_corpus
I'm sure I missed a lot, can't wait for the next week!
Put down in comments what I missed! π€
reacted to
fdaudens's
post with π
6 days ago
Post
1152
πͺ MagicQuill: AI that reads your mind for image edits! Point at what bugs you, and it suggests the perfect fixes. No more manual editing headaches. Try it here:
AI4Editing/MagicQuill
reacted to
cfahlgren1's
post with π
6 days ago
Post
2190
Why use Google Drive when you can have:
β’ Free storage with generous limitsπ
β’ Dataset Viewer (Sorting, Filtering, FTS) π
β’ Third Party Library Support
β’ SQL Console π§
β’ Security π
β’ Community, Reach, and Visibility π
It's a no brainer!
Check out our post on what you get instantly out of the box when you create a dataset.
https://huggingface.co/blog/researcher-dataset-sharing
β’ Free storage with generous limitsπ
β’ Dataset Viewer (Sorting, Filtering, FTS) π
β’ Third Party Library Support
β’ SQL Console π§
β’ Security π
β’ Community, Reach, and Visibility π
It's a no brainer!
Check out our post on what you get instantly out of the box when you create a dataset.
https://huggingface.co/blog/researcher-dataset-sharing
- 1 reply