LiquidAI/LFM2.5-Audio-1.5B
Audio-to-Audio
•
1B
•
Updated
•
1.92k
•
288
Anurag
edwixx
AI & ML interests
Machine Learning, and Speech
Recent Activity
liked
a model
1 day ago
LiquidAI/LFM2.5-Audio-1.5B
new activity
1 day ago
google/translategemma-27b-it:list of all 55 languages which are supported?
new activity
2 days ago
huggingface/InferenceSupport:edwixx/whisper-large-hebrew-finetune
Organizations
liked
a
model
1 day ago
list of all 55 languages which are supported?
7
#1 opened 5 days ago
by
edwixx
edwixx/whisper-large-hebrew-finetune
#7518 opened 2 days ago
by
edwixx
reacted to
sagar007's
post with 🤝🔥
2 days ago
Post
4088
🚀 I built a Multimodal Vision-Language Model from using Gemma-270M + CLIP!
Just finished training my multimodal model on the full LLaVA-Instruct-150K dataset (157K samples) and wanted to share the results!
🔧 What I Built:
A vision-language model that can understand images and answer questions about them, combining:
- Google Gemma-3-270M (language)
- OpenAI CLIP ViT-Large/14 (vision)
- LoRA fine-tuning for efficiency
📊 Training Stats:
- 157,712 training samples (full LLaVA dataset)
- 3 epochs on A100 40GB
- ~9 hours training time
- Final loss: 1.333 training / 1.430 validation
- Only 18.6M trainable params (3.4% of 539M total)
📈 sagar007/multigemma
Benchmark Results:
- VQA Accuracy: 53.8%
- Works great for: animal detection, room identification, scene understanding
🔗 **Try it yourself:**
- 🤗 Model: sagar007/multigemma
- 🎮 Demo: https://huggingface.co/spaces/sagar007/Multimodal-Gemma
- 💻 GitHub: https://github.com/sagar431/multimodal-gemma-270m
Built with PyTorch Lightning + MLflow for experiment tracking. Full MLOps pipeline with CI/CD!
Would love to hear your feedback! 🙏
#multimodal #gemma #clip #llava #vision-language #pytorch
Just finished training my multimodal model on the full LLaVA-Instruct-150K dataset (157K samples) and wanted to share the results!
🔧 What I Built:
A vision-language model that can understand images and answer questions about them, combining:
- Google Gemma-3-270M (language)
- OpenAI CLIP ViT-Large/14 (vision)
- LoRA fine-tuning for efficiency
📊 Training Stats:
- 157,712 training samples (full LLaVA dataset)
- 3 epochs on A100 40GB
- ~9 hours training time
- Final loss: 1.333 training / 1.430 validation
- Only 18.6M trainable params (3.4% of 539M total)
📈 sagar007/multigemma
Benchmark Results:
- VQA Accuracy: 53.8%
- Works great for: animal detection, room identification, scene understanding
🔗 **Try it yourself:**
- 🤗 Model: sagar007/multigemma
- 🎮 Demo: https://huggingface.co/spaces/sagar007/Multimodal-Gemma
- 💻 GitHub: https://github.com/sagar431/multimodal-gemma-270m
Built with PyTorch Lightning + MLflow for experiment tracking. Full MLOps pipeline with CI/CD!
Would love to hear your feedback! 🙏
#multimodal #gemma #clip #llava #vision-language #pytorch
- 9 replies
liked
2
models
4 days ago
Liquid AI, You NEED to Make a 16B MoE Next!
❤️
6
5
#5 opened 5 days ago
by
tanyiades
liked
a
model
5 days ago
upvoted
a
collection
5 days ago
updated
a
model
7 days ago
published
a
model
7 days ago
liked
a
model
7 days ago
liked
a
dataset
7 days ago
liked
a
dataset
8 days ago
updated
a
model
9 days ago
published
a
model
9 days ago
updated
a
model
9 days ago
published
a
model
9 days ago
reacted to
hypothetical's
post with 😎
11 days ago
Post
2010
We have updated our transcription model:
TheStageAI/thewhisper-large-v3-turbo
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
- 2 replies