Tahir's picture

Tahir

TahirC

·

AI & ML interests

None yet

Recent Activity

reacted to KaiChen1998's post with 👍 7 days ago

📢 Our EMOVA paper has been accepted by CVPR 2025, and we are glad to release all resources, including code (training & inference), datasets (training & evaluation), and checkpoints (EMOVA-3B/7B/72B)! 🤗 EMOVA is a novel end-to-end omni-modal LLM that can see, hear and speak. Given omni-modal (i.e., textual, visual and speech) inputs, EMOVA can generate both textual and speech responses with vivid emotional controls by utilizing the speech decoder and a style controller. ✨ EMOVA Highlights ✅ State-of-the-art omni-modality: EMOVA achieves SoTA comparable results on both vision-language and speech benchmarks simultaneously. ✅ Device adaptation: our codebase supports training/inference on both NVIDIA GPUs (e.g., A800 & H20) and Ascend NPUs (e.g., 910B3)! ✅ Modular design: we integrate multiple implementations of vision encoder, vision projector, and language model, even including the most recent DeepSeekMoE-tiny! 🔥 You are all welcome to try and star! - Project page: https://emova-ollm.github.io/ - Github: https://github.com/emova-ollm/EMOVA - Demo: https://huggingface.co/spaces/Emova-ollm/EMOVA-demo

upvoted an article 10 days ago

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

new activity 11 days ago

Remade-AI/Deflate:is there notebook for training lora like this ?

View all activity

Organizations

TahirC's activity

New activity in Remade-AI/Deflate 11 days ago

is there notebook for training lora like this ?

#1 opened 11 days ago by

New activity in strangerzonehf/Casual-Pencil-Pro 11 days ago

Can you share image labelling and lora training resources

#1 opened 11 days ago by

New activity in unsloth/Qwen2.5-VL-7B-Instruct 21 days ago

Trouble with running the model

#2 opened 24 days ago by

New activity in unsloth/Qwen2.5-VL-72B-Instruct 21 days ago

difference from Qwen/Qwen2.5-VL-72B-Instruct

#2 opened 23 days ago by

New activity in unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit 26 days ago

Huggingface code to inference this model

#1 opened about 2 months ago by

New activity in unsloth/README about 1 month ago

Fix preprocessor_config.json for Qwen2.5-VL models

#7 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-72B-Instruct-bnb-4bit about 1 month ago

Update preprocessor_config.json

#3 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit about 1 month ago

Update preprocessor_config.json

#2 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-72B-Instruct about 1 month ago

Update preprocessor_config.json

#1 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-3B-Instruct-bnb-4bit about 1 month ago

Update preprocessor_config.json

#1 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-7B-Instruct about 1 month ago

Update preprocessor_config.json

#1 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit about 1 month ago

Update preprocessor_config.json

#1 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit about 1 month ago

Update preprocessor_config.json

#2 opened about 1 month ago by

New activity in unsloth/Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit about 1 month ago

Update image_processor_type to "Qwen2VLImageProcessor"

#2 opened about 1 month ago by

Need to Update image_processor_type to Qwen2VLImageProcessor

#1 opened about 1 month ago by

New activity in Qwen/Qwen2.5-VL-7B-Instruct about 2 months ago

Provided code snippet not working?

#4 opened about 2 months ago by