Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models
Paper
•
2408.15518
•
Published
•
43
•
4
Zack Li PRO
zackli4ai
AI & ML interests
LLM, on-device AI
Recent Activity
updated
a model
8 days ago
nexa-collaboration/output_llama3.1_8b_instruct_torchao_sparsity0.7
updated
a model
8 days ago
nexa-collaboration/output_llama3.1_8b_instruct_torchao_sparsity0.2
updated
a model
8 days ago
nexa-collaboration/output_llama3.1_8b_instruct_torchao_sparsity0.3
Organizations
zackli4ai's activity
Upload RWKV-x060-World-3B-v2.1-20240417-ctx4096.pth
#2 opened 3 months ago
by
Davidqian123
Upload rwkv-3b.st
1
#1 opened 3 months ago
by
Davidqian123
Compare with llava-onevision-894M and internvl2-938M?
3
#7 opened 3 months ago
by
nemonameless
nexa-on-colab
1
#8 opened 3 months ago
by
sdyy
How to call it through transformer
2
#4 opened 3 months ago
by
awelker
transformers version?
1
#5 opened 3 months ago
by
CHNtentes
Prior art
12
#2 opened 6 months ago
by
ehartford
Longest Context is 512？
1
#1 opened 6 months ago
by
Pony
commented
a
paper
6 months ago
commented
2
papers
8 months ago
Update README.md
#9 opened 9 months ago
by
ZoeyShu
Update README.md
#4 opened 9 months ago
by
ZoeyShu
The purpose of generating a Function description
3
#4 opened 11 months ago
by
madroid
End-to-End code sample / setup with 'Routing LLM' and 'Specialist LLMs'
2
#4 opened 10 months ago
by
christianweyer
Custom categories?
3
#5 opened 9 months ago
by
huggingfacess
Update README.md
#6 opened 9 months ago
by
ZoeyShu
Update app.py
#2 opened 9 months ago
by
JoyboyBrian
Model(s) are not in Ollama registry
2
#2 opened 10 months ago
by
christianweyer
Upload Octopus-v4-Q2_K.gguf
1
#1 opened 10 months ago
by
ThunderBeee