issues
search
DNGros
/
lmwrapper
An object-oriented wrapper around language models (like openai endpoints or huggingface)
1
stars
1
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Dev
#35
DNGros
closed
7 months ago
0
Newvllm
#34
DNGros
opened
7 months ago
0
Bump openai package version
#33
claudiosv
closed
7 months ago
0
vLLM, Accelerate, and some ExLLama
#32
claudiosv
closed
7 months ago
1
Add api for sampling more than once
#31
DNGros
opened
7 months ago
0
Organization id settings via environoment variable
#30
DNGros
opened
7 months ago
0
Pytest cleverness to only load huggingface models once in test_huggingface
#29
DNGros
opened
8 months ago
0
Mistralfixes
#28
DNGros
closed
8 months ago
1
vLLM and ExLlamaV2 Work
#27
claudiosv
closed
7 months ago
0
Weird whitespace on first token of Mistral output
#26
DNGros
closed
7 months ago
1
Ability to specify differing token limits for inputs and outputs
#25
DNGros
opened
9 months ago
0
vLLM Support
#24
claudiosv
opened
11 months ago
0
Accelerate Support
#23
claudiosv
opened
11 months ago
0
Lm mem
#22
DNGros
closed
11 months ago
0
Add top tokens
#21
DNGros
closed
1 year ago
0
Let api keys be project-specific file
#20
DNGros
opened
1 year ago
0
Fix 18 codellama
#19
DNGros
closed
1 year ago
1
CodeLLaMa stop tokens sometimes breaking
#18
DNGros
closed
1 year ago
1
Code Llama
#17
claudiosv
closed
1 year ago
1
Linting & Formatting
#16
claudiosv
closed
1 year ago
1
Refactors
#15
claudiosv
closed
1 year ago
0
Test regular NL encoder-decoder
#14
DNGros
opened
1 year ago
0
Get a Encoder-decoder model running in CI
#13
DNGros
opened
1 year ago
0
Fix stop tokens and add CodeT5+ support
#12
claudiosv
closed
1 year ago
1
Claudio dev
#11
claudiosv
closed
1 year ago
0
Specify device
#10
claudiosv
closed
1 year ago
0
Rate limit IGNORE
#9
claudiosv
closed
1 year ago
0
Add token stopping and truncation
#8
claudiosv
closed
1 year ago
0
Add rate limiting
#7
claudiosv
closed
1 year ago
0
Top Tokens
#6
DNGros
opened
1 year ago
3
Add thread safe rate limiting
#5
claudiosv
closed
1 year ago
0
Fix build
#4
claudiosv
closed
1 year ago
0
Fix build
#3
claudiosv
closed
1 year ago
0
Add preliminary support for CodeGen models and start of fast inference
#2
claudiosv
closed
1 year ago
1
Faster inference
#1
claudiosv
closed
1 year ago
4