Sleeping
🏔
Emídio Souza
emidiosouza
·
AI & ML interests
None yet
Recent Activity
updated
a Space
about 1 month ago
kukac/GeoCosmos2.0
Organizations
emidiosouza's activity
updated
a
Space
about 1 month ago
updated
a
Space
2 months ago
reacted to
singhsidhukuldeep's
post with 🔥
4 months ago
Post
2575
Good folks at Meta has just unveiled Llama 3.2, pushing the boundaries of language models and computer vision.
Even more interesting is how they trained this cutting-edge model:
1️⃣ Architecture:
Llama 3.2 uses an optimized transformer architecture with auto-regressive capabilities. The largest models (11B and 90B) now support multimodal inputs, integrating both text and images.
2️⃣ Training Pipeline:
• Started with pretrained Llama 3.1 text models
• Added image adapters and encoders
• Pretrained on large-scale noisy (image, text) pair data
• Fine-tuned on high-quality in-domain and knowledge-enhanced (image, text) pairs
3️⃣ Vision Integration:
• Trained adapter weights to integrate a pre-trained image encoder
• Used cross-attention layers to feed image representations into the language model
• Preserved text-only capabilities by not updating language model parameters during adapter training
4️⃣ Post-Training Alignment:
• Multiple rounds of supervised fine-tuning (SFT)
• Rejection sampling (RS)
• Direct preference optimization (DPO)
• Synthetic data generation using Llama 3.1 for Q&A augmentation
• Reward model ranking for high-quality fine-tuning data
5️⃣ Lightweight Models:
• Used pruning and distillation techniques for 1B and 3B models
• Structured pruning from Llama 3.1 8B model
• Knowledge distillation using Llama 3.1 8B and 70B as teachers
6️⃣ Context Length:
All models support an impressive 128K token context length.
7️⃣ Safety Measures:
Incorporated safety mitigation data to balance helpfulness and safety.
The result? A suite of models ranging from edge-friendly 1B parameters to powerful 90B parameter versions, capable of sophisticated reasoning across text and images. Llama 3.2 is set to revolutionize AI applications from mobile devices to enterprise-scale solutions.
What are your thoughts on these advancements? How do you see Llama 3.2 impacting your industry? Let's discuss in the comments!
Even more interesting is how they trained this cutting-edge model:
1️⃣ Architecture:
Llama 3.2 uses an optimized transformer architecture with auto-regressive capabilities. The largest models (11B and 90B) now support multimodal inputs, integrating both text and images.
2️⃣ Training Pipeline:
• Started with pretrained Llama 3.1 text models
• Added image adapters and encoders
• Pretrained on large-scale noisy (image, text) pair data
• Fine-tuned on high-quality in-domain and knowledge-enhanced (image, text) pairs
3️⃣ Vision Integration:
• Trained adapter weights to integrate a pre-trained image encoder
• Used cross-attention layers to feed image representations into the language model
• Preserved text-only capabilities by not updating language model parameters during adapter training
4️⃣ Post-Training Alignment:
• Multiple rounds of supervised fine-tuning (SFT)
• Rejection sampling (RS)
• Direct preference optimization (DPO)
• Synthetic data generation using Llama 3.1 for Q&A augmentation
• Reward model ranking for high-quality fine-tuning data
5️⃣ Lightweight Models:
• Used pruning and distillation techniques for 1B and 3B models
• Structured pruning from Llama 3.1 8B model
• Knowledge distillation using Llama 3.1 8B and 70B as teachers
6️⃣ Context Length:
All models support an impressive 128K token context length.
7️⃣ Safety Measures:
Incorporated safety mitigation data to balance helpfulness and safety.
The result? A suite of models ranging from edge-friendly 1B parameters to powerful 90B parameter versions, capable of sophisticated reasoning across text and images. Llama 3.2 is set to revolutionize AI applications from mobile devices to enterprise-scale solutions.
What are your thoughts on these advancements? How do you see Llama 3.2 impacting your industry? Let's discuss in the comments!
liked
a
model
4 months ago
updated
2
Spaces
6 months ago
liked
a
Space
6 months ago