4 31

Qiang

mikv39

null-define

AI & ML interests

None yet

Recent Activity

reacted to m-ric's post with 🚀 1 day ago

New king of open VLMs: InternVL3 takes Qwen 2.5's crown! 👑 InternVL have been a wildly successful series of model : and the latest iteration has just taken back their crown thanks to their superior, natively multimodal vision training pipeline. ➡️ Most of the vision language models (VLMs) these days are built like Frankenstein : take a good text-only Large Language Model (LLM) backbone, stitch a specific vision transformer (ViT) on top of it. Then the training is sequential 🔢 : 1. Freeze the LLM weights while you train the ViT only to work with the LLM part, then 2. Unfreeze all weights to train all weights in order to work together. 💫 The Shanghai Lab decided to challenge this paradigm and chose this approach that they call "native". For each of their model sizes, they still start from a good LLM (mostly Qwen-2.5 series, did I tell you I'm a huge fan of Qwen? ❤️), and stitch the ViT, but they don't freeze anything : they train all weights together with interleaved text and image understanding data in a single pre-training phase 🎨. They claim it results in more seamless interactions between modalities. And the results prove them right: they took the crown of top VLMs, at nearly all sizes, from their Qwen-2.5 parents. 👑

reacted to davidberenstein1957's post with 🤗 1 day ago

🧑‍🏫 I wrote a brief blogpost to give An Introduction to AI Model Optimization Techniques! URL: https://huggingface.co/blog/PrunaAI/introduction-to-ai-model-optimization-techniques

liked a model 2 days ago

bartowski/dreamgen_lucid-v1-nemo-GGUF

View all activity

Organizations

None yet

mikv39's activity

liked a model 2 days ago

bartowski/dreamgen_lucid-v1-nemo-GGUF

Text Generation • Updated 3 days ago • 2.83k • 4

liked a model 6 days ago

qualcomm/Whisper-Small-V2

Automatic Speech Recognition • Updated 10 days ago • 3

liked a model 9 days ago

moonshotai/Kimi-VL-A3B-Thinking

Image-Text-to-Text • Updated 5 days ago • 25k • 364

liked a model 13 days ago

ibm-granite/granite-speech-3.2-8b

Automatic Speech Recognition • Updated 3 days ago • 3.1k • 75

liked a model 14 days ago

bartowski/inclusionAI_Ling-lite-GGUF

Text Generation • Updated 17 days ago • 3k • 2

liked a model 16 days ago

Orion-zhen/Qwen2.5-7B-Gutenberg-KTO

Text Generation • Updated Oct 12, 2024 • 10 • 5

liked a model 24 days ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated 5 days ago • 161k • 1.43k

liked a model 29 days ago

Sao10K/Llama-3.3-70B-Vulpecula-r1

Text Generation • Updated about 1 month ago • 1.33k • 36

liked 2 models about 1 month ago

mollysama/rwkv-mobile-models

Updated about 3 hours ago • 3.28k • 5

BlinkDL/rwkv7-g1

Text Generation • Updated 26 days ago • 73

liked 3 datasets about 1 month ago

liked 3 models about 1 month ago

Undi95/QwQ-RP-GGUF

Updated Mar 7 • 457 • 10

Undi95/QwQ-RP-LoRA

Updated Mar 7 • 13 • 2

hexgrad/Kokoro-82M-v1.1-zh

Text-to-Speech • Updated Mar 4 • 37.6k • 105

liked 3 models about 2 months ago

sthenno-com/miscii-14b-0218

Text Generation • Updated Mar 10 • 170 • 22

ibm-granite/granite-3.2-8b-instruct

Text Generation • Updated 2 days ago • 50.3k • 79

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • Updated 11 days ago • 634k • 1.31k

liked a model 2 months ago

yuyouyu/Mistral-Nemo-BD-RP

Question Answering • Updated Aug 30, 2024 • 16 • 7