deepseek-ai/DeepSeek-V4-Flash
Text Generation • 158B • Updated • 23 • 398
Victor C.
dehnhaide
AI & ML interests
None yet
Recent Activity
liked a model 5 minutes ago
deepseek-ai/DeepSeek-V4-Flash liked a model about 14 hours ago
AesSedai/Kimi-K2.6-GGUF liked a model about 14 hours ago
ubergarm/Kimi-K2.6-GGUFOrganizations
None yet
liked a
model 5 minutes ago
liked 2
models about 14 hours ago
liked a
model 4 days ago
liked 2
models 7 days ago
Excellent 5.00 bps quant
#2 opened 7 days ago
by dehnhaide
liked 2
models 7 days ago
Hoping for your magic on MiniMax-M2.7-FP8-INT4-AWQ quant
17
#2 opened 12 days ago
by dehnhaide
liked a
model 7 days ago
Testing Q5 flavors (ubergarm / aessedai / unsloth) for "speed" on 8x RTX 3090
🔥 1
2
#10 opened 8 days ago
by dehnhaide
UD-Q4_K_XL of MiniMax-M2.7-GGUF in BROKEN
8
#5 opened 11 days ago
by dehnhaide
An upgrade in quality and a mixed bag of ... 8x RTX3090
1
#3 opened 9 days ago
by dehnhaide
liked 2
models 11 days ago
GLM 5.1 vs GLM 5 - burns A LOT output tokens on thinking
👍 1
35
#6 opened 13 days ago
by 
curiouspp8
reacted to Juanxi's post with 🚀 11 days ago
Post
4398
📢 Awesome Multimodal Modeling
We introduce Awesome Multimodal Modeling, a curated repository tracing the architectural evolution of multimodal intelligence—from foundational fusion to native omni-models.
🔹 Taxonomy & Evolution:
Traditional Multimodal Learning – Foundational work on representation, fusion, and alignment.
Multimodal LLMs (MLLMs) – Architectures connecting vision encoders to LLMs for understanding.
Unified Multimodal Models (UMMs) – Models unifying Understanding + Generation via Diffusion, Autoregressive, or Hybrid paradigms.
Native Multimodal Models (NMMs) – Models trained from scratch on all modalities; contrasts early vs. late fusion under scaling laws.
💡 Key Distinction:
UMMs unify tasks via generation heads; NMMs enforce interleaving through joint pre-training.
🔗 Explore & Contribute: https://github.com/OpenEnvision/Awesome-Multimodal-Modeling
We introduce Awesome Multimodal Modeling, a curated repository tracing the architectural evolution of multimodal intelligence—from foundational fusion to native omni-models.
🔹 Taxonomy & Evolution:
Traditional Multimodal Learning – Foundational work on representation, fusion, and alignment.
Multimodal LLMs (MLLMs) – Architectures connecting vision encoders to LLMs for understanding.
Unified Multimodal Models (UMMs) – Models unifying Understanding + Generation via Diffusion, Autoregressive, or Hybrid paradigms.
Native Multimodal Models (NMMs) – Models trained from scratch on all modalities; contrasts early vs. late fusion under scaling laws.
💡 Key Distinction:
UMMs unify tasks via generation heads; NMMs enforce interleaving through joint pre-training.
🔗 Explore & Contribute: https://github.com/OpenEnvision/Awesome-Multimodal-Modeling
- 2 replies
Question about benchmark results
🔥🚀 2
8
#5 opened about 2 months ago
by 
tarruda
liked a
model 12 days ago
