Running
on
CPU Upgrade
9.13k
π©βπ¨
AI Comic Factory
Create your own AI comic with a single prompt
Simeon Emanuilov PRO
s-emanuilov
AI & ML interests
Software Engineer & Ph.D. candidate | Specializing in ML/DL system development & applying AI to solve real-world business problems.
Recent Activity
liked
a Space
about 20 hours ago
jbilcke-hf/ai-comic-factory
liked
a Space
about 20 hours ago
FaceOnLive/Face-Search-Online
upvoted
a
collection
about 21 hours ago
Jan 17 Releases βοΈ
Organizations
s-emanuilov's activity
liked
2
Spaces
about 20 hours ago
upvoted
a
collection
about 21 hours ago
reacted to
merve's
post with β€οΈ
about 21 hours ago
Post
795
Everything that happened this week in open AI, a recap π€
merve/jan-17-releases-678a673a9de4a4675f215bf5
π Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
π¬ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens π€―
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D π§π»ββοΈ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
πΌοΈ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
π£οΈ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
π Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
π Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
π¬ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens π€―
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D π§π»ββοΈ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
πΌοΈ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
π£οΈ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
π Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
upvoted
2
papers
1 day ago
commented
a
paper
1 day ago
liked
a
model
2 days ago
reacted to
tomaarsen's
post with β€οΈ
2 days ago
Post
4094
ποΈ Today I'm introducing a method to train static embedding models that run 100x to 400x faster on CPU than common embedding models, while retaining 85%+ of the quality! Including 2 fully open models: training scripts, datasets, metrics.
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2οΈβ£ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
π§ my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
π my training scripts, using the Sentence Transformers library
π my Weights & Biases reports with losses & metrics
π my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
ποΈ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0οΈβ£ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
π No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
π Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
πͺ Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2οΈβ£ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
π§ my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
π my training scripts, using the Sentence Transformers library
π my Weights & Biases reports with losses & metrics
π my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
ποΈ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0οΈβ£ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
π No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
π Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
πͺ Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
- 1 reply
upvoted
a
paper
2 days ago
updated
a
collection
2 days ago
commented
2
papers
2 days ago
upvoted
a
paper
2 days ago
commented
a
paper
2 days ago
posted
an
update
2 days ago
Post
388
A new benchmark (DPAB-Ξ±) has been released that evaluates LLM function calling in both Pythonic and JSON approaches.
It shows that Pythonic function calling often outperforms traditional JSON-based methods, especially for complex multi-step tasks.
Key findings from benchmarks:
β Claude 3.5 Sonnet leads with 87% on Pythonic vs 45% on JSON
β Smaller models show impressive results (Dria-Agent-Ξ±-3B: 72% Pythonic)
β Even larger models like DeepSeek V3 (685B) show significant gaps (63% Pythonic vs 33% JSON)
If you're building or using LLM agents, these results suggest that how you implement function calling could impact performance - might be worth reconsidering JSON-only approaches.
The benchmark: https://github.com/firstbatchxyz/function-calling-eval
Blog post: https://huggingface.co/blog/andthattoo/dpab-a
It shows that Pythonic function calling often outperforms traditional JSON-based methods, especially for complex multi-step tasks.
Key findings from benchmarks:
β Claude 3.5 Sonnet leads with 87% on Pythonic vs 45% on JSON
β Smaller models show impressive results (Dria-Agent-Ξ±-3B: 72% Pythonic)
β Even larger models like DeepSeek V3 (685B) show significant gaps (63% Pythonic vs 33% JSON)
If you're building or using LLM agents, these results suggest that how you implement function calling could impact performance - might be worth reconsidering JSON-only approaches.
The benchmark: https://github.com/firstbatchxyz/function-calling-eval
Blog post: https://huggingface.co/blog/andthattoo/dpab-a
reacted to
AdinaY's
post with π₯
3 days ago
Post
2896
MiniMax, the company behind Hailuo_AI, has joined the open source community by releasing both models and demos of MiniMax-Text-01 & MiniMax-VL-01π₯
- Model
MiniMaxAI/MiniMax-VL-01
MiniMaxAI/MiniMax-Text-01
- Demo
MiniMaxAI/MiniMax-VL-01
MiniMaxAI/MiniMax-Text-01
β¨ MiniMax-text-01:
- 456B with 45.9B activated per token
- Combines Lightning Attention, Softmax Attention, and MoE for optimal performance
- Training context up to 1M tokens, inference handles 4M tokens
β¨ MiniMax-VL-01:
- ViT-MLP-LLM framework ( non-transformerπ)
- Handles image inputs from 336Γ336 to 2016Γ2016
- 694M image-caption pairs + 512B tokens processed across 4 stages
- Model
MiniMaxAI/MiniMax-VL-01
MiniMaxAI/MiniMax-Text-01
- Demo
MiniMaxAI/MiniMax-VL-01
MiniMaxAI/MiniMax-Text-01
β¨ MiniMax-text-01:
- 456B with 45.9B activated per token
- Combines Lightning Attention, Softmax Attention, and MoE for optimal performance
- Training context up to 1M tokens, inference handles 4M tokens
β¨ MiniMax-VL-01:
- ViT-MLP-LLM framework ( non-transformerπ)
- Handles image inputs from 336Γ336 to 2016Γ2016
- 694M image-caption pairs + 512B tokens processed across 4 stages
- 1 reply
liked
2
models
3 days ago
upvoted
a
paper
3 days ago