Post
1111
- 1 reply
Adam Molnar
lunarflu
AI & ML interests
join the Hugging Face discord! hf.co/discord/join
Recent Activity
updated
a Space
26 minutes ago
discord-community/LevelBot
Organizations
lunarflu's activity
reacted to
sequelbox's
post with 👍
3 days ago
reacted to
reach-vb's
post with 🚀🤗👍🔥
3 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! 🤗
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! 🤗
reacted to
TuringsSolutions's
post with 👀
3 days ago
Post
691
If I am correct and the LLM model changes the 'shape' of the data as it learns, then I should be able to track and utilize those shape changes as a backpropagation training mechanism, right? Well guess what, I can do that! Entropy, Sparsity, and Density, this is how I can measure the shape of the data the LLM model is creating. Nodes, Clusters, and Edges, these are the mechanisms within the neural network the LLM model updates as it learns these concepts. I measure the effects of these updates, via Entropy, Sparsity, and Density. Check out more in this video: https://youtu.be/jADTt5HHtiw
- 2 replies
reacted to
erikkaum's
post with 👀🔥
3 days ago
Post
1611
A while ago I started experimenting with compiling the Python interpreter to WASM.
To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
Hack away:
https://github.com/ErikKaum/runner
To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
Hack away:
https://github.com/ErikKaum/runner
reacted to
AdinaY's
post with 👀
3 days ago
Post
1385
LLaMA Mesh 🔥 Unifying 3D Mesh Generation with Language Models
Model: Zhengyi/LLaMA-Mesh
Demo: Zhengyi/LLaMA-Mesh
Paper: LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models (2411.09595)
✨ Unified 3D generation & text understanding.
✨ 3D meshes as plain text for seamless LLM integration.
✨ High-quality 3D outputs rivaling specialized models.
Model: Zhengyi/LLaMA-Mesh
Demo: Zhengyi/LLaMA-Mesh
Paper: LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models (2411.09595)
✨ Unified 3D generation & text understanding.
✨ 3D meshes as plain text for seamless LLM integration.
✨ High-quality 3D outputs rivaling specialized models.
reacted to
sayakpaul's
post with 🚀❤️
3 days ago
Post
2069
It's been a while we shipped native quantization support in
We currently support
This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
diffusers 🧨We currently support
bistandbytes as the official backend but using others like torchao is already very simple. This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
enable_model_cpu_offload()5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
- 1 reply
reacted to
davidberenstein1957's
post with 🤗🧠🚀😎🔥👀
3 days 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 🙂
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 🙂
reacted to
Ameeeee's
post with 👀
3 days ago
Post
1186
Build a fine-tuning dataset with No Code.
Do you want to build a small dataset for creative writing to fine-tune an Open LLM?
- Find a dataset full of conversations with ChatGPT on the Hugging Face Hub.
- Import it into your Argilla Space.
- Preview the dataset and create a question to label the relevant conversations.
- Label 1000 valid examples of creating writing.
- Use this dataset with Autotrain to fine-tune your model.
Do you want to build a small dataset for creative writing to fine-tune an Open LLM?
- Find a dataset full of conversations with ChatGPT on the Hugging Face Hub.
- Import it into your Argilla Space.
- Preview the dataset and create a question to label the relevant conversations.
- Label 1000 valid examples of creating writing.
- Use this dataset with Autotrain to fine-tune your model.
- 1 reply
reacted to
merve's
post with 🚀
3 days ago
Post
1574
🤗 transformers pipelines now support vision language models for easy local inference 🫰🏻
h/t @yonigozlan for shipping this 🎩👏
you can also use inference API to infer hosted vision LMs (via Python, JS and cURL) https://huggingface.co/docs/api-inference/en/tasks/image-text-to-text
h/t @yonigozlan for shipping this 🎩👏
you can also use inference API to infer hosted vision LMs (via Python, JS and cURL) https://huggingface.co/docs/api-inference/en/tasks/image-text-to-text
reacted to
csabakecskemeti's
post with 👍
3 days ago
Post
1186
Some time ago, I built a predictive LLM router that routes chat requests between small and large LLM models based on prompt classification. It dynamically selects the most suitable model depending on the complexity of the user input, ensuring optimal performance while maintaining conversation context. I also fine-tuned a RoBERTa model to use with the package, but you can plug and play any classifier of your choice.
Project's homepage:
https://devquasar.com/llm-predictive-router/
Pypi:
https://pypi.org/project/llm-predictive-router/
Model:
DevQuasar/roberta-prompt_classifier-v0.1
Training data:
DevQuasar/llm_router_dataset-synth
Git:
https://github.com/csabakecskemeti/llm_predictive_router_package
Feel free to check it out, and/or contribute.
Project's homepage:
https://devquasar.com/llm-predictive-router/
Pypi:
https://pypi.org/project/llm-predictive-router/
Model:
DevQuasar/roberta-prompt_classifier-v0.1
Training data:
DevQuasar/llm_router_dataset-synth
Git:
https://github.com/csabakecskemeti/llm_predictive_router_package
Feel free to check it out, and/or contribute.