Llama can now see and run on your device - welcome Llama 3.2
•
167
Merve Noyan
merve
AI & ML interests
VLMs, vision & co
Articles
Organizations
Posts
71
Post
608
OmniVision-968M: a new local VLM for edge devices, fast & small but performant
💨 a new vision language model with 9x less image tokens, super efficient
📖 aligned with DPO for reducing hallucinations
⚡️ Apache 2.0 license 🔥
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M
💨 a new vision language model with 9x less image tokens, super efficient
📖 aligned with DPO for reducing hallucinations
⚡️ Apache 2.0 license 🔥
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M
Post
1712
Amazing past days at open ML, it's raining coding models, let's have a recap 🌧️ Find all models and datasets here
merve/nov-15-releases-67372d0ebdc354756a52ecd0
Models
💻 Coding: Qwen team released two Qwen2.5-Coder checkpoints of 32B and 7B. Infly released OpenCoder: 1.5B and 8B coding models with instruction SFT'd versions and their datasets! 💗
🖼️ Image/Video Gen: Alibaba vision lab released In-context LoRA -- 10 LoRA models on different themes based on Flux. Also Mochi the sota video generation model with A2.0 license now comes natively supported in diffusers 👏
🖼️ VLMs/Multimodal: NexaAIDev released Omnivision 968M a new vision language model aligned with DPO for reducing hallucinations, also comes with GGUF ckpts 👏 Microsoft released LLM2CLIP, a new CLIP-like model with longer context window allowing complex text inputs and better search
🎮 AGI?: Etched released Oasis 500M, a diffusion based open world model that takes keyboard input and outputs gameplay 🤯
Datasets
Common Corpus: A text dataset with 2T tokens with permissive license for EN/FR on various sources: code, science, finance, culture 📖
Models
💻 Coding: Qwen team released two Qwen2.5-Coder checkpoints of 32B and 7B. Infly released OpenCoder: 1.5B and 8B coding models with instruction SFT'd versions and their datasets! 💗
🖼️ Image/Video Gen: Alibaba vision lab released In-context LoRA -- 10 LoRA models on different themes based on Flux. Also Mochi the sota video generation model with A2.0 license now comes natively supported in diffusers 👏
🖼️ VLMs/Multimodal: NexaAIDev released Omnivision 968M a new vision language model aligned with DPO for reducing hallucinations, also comes with GGUF ckpts 👏 Microsoft released LLM2CLIP, a new CLIP-like model with longer context window allowing complex text inputs and better search
🎮 AGI?: Etched released Oasis 500M, a diffusion based open world model that takes keyboard input and outputs gameplay 🤯
Datasets
Common Corpus: A text dataset with 2T tokens with permissive license for EN/FR on various sources: code, science, finance, culture 📖
spaces
104
models
88
merve/paligemma_vqav2
Image-Text-to-Text
•
Updated
•
215
•
10
merve/google-ckpts
Updated
merve/google-tokenizers
Updated
merve/siglip-so400m-patch16-256-i18n
Updated
•
37
•
9
merve/idefics3-llama-vqav2
Updated
merve/idefics3llama-vqav2
Updated
•
8
merve/flux-dreambooth-lora
Updated
•
1
merve/trained-flux-lora-lego
Text-to-Image
•
Updated
•
12
•
•
1
merve/flux-lego-lora-dreambooth
Text-to-Image
•
Updated
•
2.33k
•
•
13
merve/sam2-hiera-large
Mask Generation
•
Updated
•
136k
•
2
datasets
26
merve/model-test-inputs
Updated
•
50
merve/vqav2-small
Viewer
•
Updated
•
21.4k
•
991
•
7
merve/SGinW
Preview
•
Updated
•
387
merve/pascal-voc
Viewer
•
Updated
•
336k
•
526
merve/YouCook2
Viewer
•
Updated
•
2k
•
55
merve/faiss_embeddings
Updated
•
20
merve/pokemon-ds-embeddings
Viewer
•
Updated
•
833
•
58
•
4
merve/tr-h4-norobots
Updated
•
57
•
10
merve/lego_sets_latest
Viewer
•
Updated
•
61
•
176
•
2
merve/ai-tube-dummy
Updated
•
54