Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance
Paper
•
2409.13757
•
Published
Ditto
dittops
·
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
budecosystem/code-millenials-1b:Adding `safetensors` variant of this model
authored
a paper
5 months ago
Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with
Selective Cloud Assistance
new activity
8 months ago
budecosystem/boomer-bitnet-634m:Possible to run with llama.cpp now?
Organizations
dittops's activity
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
authored
a
paper
5 months ago
Possible to run with llama.cpp now?
2
#1 opened 8 months ago
by
BoscoTheDog
authored
a
paper
8 months ago
updated
a
dataset
10 months ago
authored
a
paper
10 months ago
updated
3
models
10 months ago
Longer inference time
2
#4 opened 11 months ago
by
dittops
Adding Evaluation Results
#2 opened 11 months ago
by
leaderboard-pr-bot
updated
a
model
11 months ago
Update boomer_code_tokenizer.py
#1 opened about 1 year ago
by
mike-ravkine
updated
a
model
about 1 year ago
Could you please confirm prompt template?
1
#1 opened about 1 year ago
by
KrisPi
updated
2
models
about 1 year ago
liked
a
model
about 1 year ago
Is this tokenizer messed up?
2
#3 opened over 1 year ago
by
joeofportland
updated
a
model
over 1 year ago