DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning
Text Generation
•
1B
•
Updated
•
551
•
5
Emre Dalkıran
iojvsuynv
·
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning
liked
a model
12 days ago
DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus
liked
a model
12 days ago
DavidAU/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
Organizations
None yet
liked
3
models
12 days ago
liked
a
Space
6 months ago
reacted to
MKhan98's
post with 👍
7 months ago
Post
320
Для рынка РФ есть желающие сделать проект?
Ищу человека, который хорош в дообучении LLM модели.
Подобные модели нашел здесь, но они заточены на англ или иероглифы – на русском пишут плохо.
Есть 500 почт от людей, которые ждут запуска B2C продукта.
Напишите в телегу: khnblv
За спиной 2 года в VK продактом и личный сторонний проект на 130к MAU.
Ищу человека, который хорош в дообучении LLM модели.
Подобные модели нашел здесь, но они заточены на англ или иероглифы – на русском пишут плохо.
Есть 500 почт от людей, которые ждут запуска B2C продукта.
Напишите в телегу: khnblv
За спиной 2 года в VK продактом и личный сторонний проект на 130к MAU.
published
a
Space
7 months ago
upvoted
a
collection
8 months ago
liked
a
model
9 months ago
reacted to
nyuuzyou's
post with 👍
9 months ago
Post
3626
🦅 SmolLM2-Eagle Collection -
nyuuzyou/smollm2-eagle-680263bf97f0c7e6bbe4936b
Collection of fine-tuned bilingual language models featuring:
- Models in three parameter sizes: 135M, 360M, and 1.7B based on HuggingFaceTB's SmolLM2 models
- Both standard and GGUF formats for flexible deployment in llama.cpp and Ollama
- Fine-tuned on nyuuzyou/EagleSFT dataset (536,231 Russian-English QA pairs derived from 739k+ real user queries)
- Experimental Russian language capabilities while maintaining English performance
- Limited Russian capabilities due to SFT-only approach without Russian pre-training
- Environmental impact: ~19.75 kg CO2eq
This collection provides compact models for research on bilingual language capabilities, resource-constrained environments, and educational applications. Not recommended for production use due to experimental nature and inherent limitations. Available under Apache 2.0 license.
Collection of fine-tuned bilingual language models featuring:
- Models in three parameter sizes: 135M, 360M, and 1.7B based on HuggingFaceTB's SmolLM2 models
- Both standard and GGUF formats for flexible deployment in llama.cpp and Ollama
- Fine-tuned on nyuuzyou/EagleSFT dataset (536,231 Russian-English QA pairs derived from 739k+ real user queries)
- Experimental Russian language capabilities while maintaining English performance
- Limited Russian capabilities due to SFT-only approach without Russian pre-training
- Environmental impact: ~19.75 kg CO2eq
This collection provides compact models for research on bilingual language capabilities, resource-constrained environments, and educational applications. Not recommended for production use due to experimental nature and inherent limitations. Available under Apache 2.0 license.
- 1 reply
liked
a
model
10 months ago
liked
a
model
12 months ago
reacted to
nroggendorff's
post with ➕
about 1 year ago
Post
6392
hey nvidia, can you send me a gpu?
comment or react if you want ~~me~~ to get one too. 👉👈
comment or react if you want ~~me~~ to get one too. 👉👈
- 33 replies
Error loading model
2
#9 opened about 1 year ago
by
iojvsuynv
reacted to
hbseong's
post with 👀
about 1 year ago
Post
943
🚨🔥 New Release Alert! 🔥🚨
Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥
👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)
More details in our paper: https://arxiv.org/abs/2410.01524 📜
#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning
Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥
👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)
More details in our paper: https://arxiv.org/abs/2410.01524 📜
#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning
- 1 reply
reacted to
singhsidhukuldeep's
post with ❤️
about 1 year ago
Post
1931
It's not every day you see the No. 1 ranked paper of the day open-sourcing a very powerful image editing app!
Fascinating to see MagicQuill - a groundbreaking interactive image editing system that makes precise photo editing effortless through advanced AI!
The system's architecture features three sophisticated components:
1. Editing Processor:
- Implements a dual-branch architecture integrated into a latent diffusion framework
- Utilizes PiDiNet for edge map extraction and content-aware per-pixel inpainting
- Features a specialized UNet architecture with zero-convolution layers for feature insertion
- Employs denoising score matching for training the control branch
- Processes both structural modifications via scribble guidance and color manipulation through downsampled color blocks
- Maintains pixel-level control through VAE-based latent space operations
2. Painting Assistor:
- Powered by a fine-tuned LLaVA multimodal LLM using Low-Rank Adaptation (LoRA)
- Trained on a custom dataset derived from Densely Captioned Images (DCI)
- Processes user brushstrokes through specialized Q&A tasks for add/subtract/color operations
- Features bounding box coordinate normalization for precise stroke localization
- Implements streamlined single-word/phrase outputs for real-time performance
3. Idea Collector:
- Built as a modular ReactJS component library
- Supports cross-platform deployment via HTTP protocols
- Compatible with Gradio and ComfyUI frameworks
- Features comprehensive layer management and parameter adjustment capabilities
- Implements real-time canvas updates and preview generation
The system outperforms existing solutions like SmartEdit and BrushNet in edge alignment and color fidelity while maintaining seamless integration with popular AI frameworks.
What are your thoughts on AI-powered creative tools?
Fascinating to see MagicQuill - a groundbreaking interactive image editing system that makes precise photo editing effortless through advanced AI!
The system's architecture features three sophisticated components:
1. Editing Processor:
- Implements a dual-branch architecture integrated into a latent diffusion framework
- Utilizes PiDiNet for edge map extraction and content-aware per-pixel inpainting
- Features a specialized UNet architecture with zero-convolution layers for feature insertion
- Employs denoising score matching for training the control branch
- Processes both structural modifications via scribble guidance and color manipulation through downsampled color blocks
- Maintains pixel-level control through VAE-based latent space operations
2. Painting Assistor:
- Powered by a fine-tuned LLaVA multimodal LLM using Low-Rank Adaptation (LoRA)
- Trained on a custom dataset derived from Densely Captioned Images (DCI)
- Processes user brushstrokes through specialized Q&A tasks for add/subtract/color operations
- Features bounding box coordinate normalization for precise stroke localization
- Implements streamlined single-word/phrase outputs for real-time performance
3. Idea Collector:
- Built as a modular ReactJS component library
- Supports cross-platform deployment via HTTP protocols
- Compatible with Gradio and ComfyUI frameworks
- Features comprehensive layer management and parameter adjustment capabilities
- Implements real-time canvas updates and preview generation
The system outperforms existing solutions like SmartEdit and BrushNet in edge alignment and color fidelity while maintaining seamless integration with popular AI frameworks.
What are your thoughts on AI-powered creative tools?
reacted to
tomaarsen's
post with 🔥
about 1 year ago
Post
5903
I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details:
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
export_static_quantized_openvino_model method to quantize a model.2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
prompts argument in SentenceTransformerTrainingArguments. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer.3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
reacted to
hbseong's
post with 👍
about 1 year ago
Post
3311
🚨🔥 New Release Alert! 🔥🚨
Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥
👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)
More details in our paper: https://arxiv.org/abs/2410.01524 📜
#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning
Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥
👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)
More details in our paper: https://arxiv.org/abs/2410.01524 📜
#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning
liked
a
model
about 1 year ago
liked
a
Space
about 1 year ago
reacted to
m-ric's
post with 🔥
over 1 year ago
Post
2958
Rhymes AI drops Aria: small Multimodal MoE that beats GPT-4o and Gemini-1.5-Flash ⚡️
New player entered the game! Rhymes AI has just been announced, and unveiled Aria – a multimodal powerhouse that's punching above its weight.
Key insights:
🧠 Mixture-of-Experts architecture: 25.3B total params, but only 3.9B active.
🌈 Multimodal: text/image/video → text.
📚 Novel training approach: “multimodal-native” where multimodal training starts directly during pre-training, not just tacked on later
📏 Long 64K token context window
🔓 Apache 2.0 license, with weights, code, and demos all open
⚡️ On the benchmark side, Aria leaves some big names in the dust.
- It beats Pixtral 12B or Llama-3.2-12B on several vision benchmarks like MMMU or MathVista.
- It even overcomes the much bigger GPT-4o on long video tasks and even outshines Gemini 1.5 Flash when it comes to parsing lengthy documents.
But Rhymes AI isn't just showing off benchmarks. They've already got Aria powering a real-world augmented search app called “Beago”. It’s handling even recent events with great accuracy!
And they partnered with AMD to make it much faster than competitors like Perplexity or Gemini search.
Read their paper for Aria 👉 Aria: An Open Multimodal Native Mixture-of-Experts Model (2410.05993)
Try BeaGo 🐶 👉 https://rhymes.ai/blog-details/introducing-beago-your-smarter-faster-ai-search
New player entered the game! Rhymes AI has just been announced, and unveiled Aria – a multimodal powerhouse that's punching above its weight.
Key insights:
🧠 Mixture-of-Experts architecture: 25.3B total params, but only 3.9B active.
🌈 Multimodal: text/image/video → text.
📚 Novel training approach: “multimodal-native” where multimodal training starts directly during pre-training, not just tacked on later
📏 Long 64K token context window
🔓 Apache 2.0 license, with weights, code, and demos all open
⚡️ On the benchmark side, Aria leaves some big names in the dust.
- It beats Pixtral 12B or Llama-3.2-12B on several vision benchmarks like MMMU or MathVista.
- It even overcomes the much bigger GPT-4o on long video tasks and even outshines Gemini 1.5 Flash when it comes to parsing lengthy documents.
But Rhymes AI isn't just showing off benchmarks. They've already got Aria powering a real-world augmented search app called “Beago”. It’s handling even recent events with great accuracy!
And they partnered with AMD to make it much faster than competitors like Perplexity or Gemini search.
Read their paper for Aria 👉 Aria: An Open Multimodal Native Mixture-of-Experts Model (2410.05993)
Try BeaGo 🐶 👉 https://rhymes.ai/blog-details/introducing-beago-your-smarter-faster-ai-search
- 1 reply