rasyosef/LFM3-1.7B-DSpark-GGUF
Text Generation • 0.3B • Updated • 817 • 1
Yosef Worku Alemneh
rasyosef
AI & ML interests
Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling
Recent Activity
new activity 2 days ago
rasyosef/gemma-4-E2B-it-dspark:Can speculators directly train Gemma4-E2B's dflash2 and dspark?Organizations
Can speculators directly train Gemma4-E2B's dflash2 and dspark?
1
#1 opened 3 days ago
by 
Rnake
⚡ Up to 5.1x faster inference with DSpark speculative decoding (71 --> 364 tokens/sec)
6
#11 opened 11 days ago
by rasyosef
⚡LFM3-1.7B-DSpark: Up to 3.1× faster LFM3-1.7B inference with a DSpark draft model (vLLM + llama.cpp)
👍 1
7
#29 opened 6 days ago
by rasyosef
a dspark model would be wonderful, even if silly
👀❤️ 3
2
#23 opened 11 days ago
by 
Smorty100
updated a
model 6 days ago
published a
model 6 days ago
updated a
model 7 days ago
published a
model 7 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
updated a
collection 8 days ago
⚡ Up to 5.1x speedup with DSpark speculative decoding (71 --> 364 tokens/sec)
#5 opened 11 days ago
by rasyosef
updated a
model 12 days ago
published a
model 12 days ago
updated a
dataset 12 days ago
published a
dataset 13 days ago
Any MTP or DFlash/DSpark drafter planned?
3
#8 opened 22 days ago
by rasyosef
Up to 4.1x speedup with a DSpark draft model for K2-Horizon-3.7B (109 --> 450 tokens/sec)
#9 opened 21 days ago
by rasyosef