remove gemma from list of models
903c035
Daniel Nichols
commited on
Spaces:
Sleeping
Sleeping
Commit History
add max code len to control length
972361d
Daniel Nichols
commited on
update documentation
63f2785
Daniel Nichols
commited on
update max tokens
a1ad1c4
Daniel Nichols
commited on
enable llama3 8b
4056573
Daniel Nichols
commited on
add timeout and gemma
3bf80a8
Daniel Nichols
commited on
add new models
e8d5b14
Daniel Nichols
commited on
update wording to remove perfguru references
837a7fe
Daniel Nichols
commited on
must explicitly ask for using local models
ae18ce3
Daniel Nichols
commited on
better error handling
f20b453
Daniel Nichols
commited on
add hf inference api and update streaming
dc10826
Daniel Nichols
commited on
fix fallback hf_home path
0cfd67a
Daniel Nichols
commited on
debugging commit
be375ad
Daniel Nichols
commited on
fix bug with return value
534f486
Daniel Nichols
commited on
fix local model loading
1519b78
Daniel Nichols
commited on
update local model loading
6a8d575
Daniel Nichols
commited on
disable download button on reprompt
9504fd5
Daniel Nichols
commited on
add download button
d672eb0
Daniel Nichols
commited on
Squashed commit of the following:
ae7d0e1
Daniel Nichols
commited on
Squashed commit of the following:
2233c73
Daniel Nichols
commited on
Add function parsing (#3)
8c0b7ca
unverified
Daniel Nichols
Mazin Karjikar
commited on
Quickstarting llama.cpp (#2)
6f00050
unverified
Mazin Karjikar
commited on
refactor error handling code
a36b415
Daniel Nichols
commited on
move token limits file to root
cf65656
Daniel Nichols
commited on
fixed num_tokens to use length of tokenization, increased max token limit
6ede84a
Mazin Karjikar
commited on
added token limits and error handling for long prompts
2c0daa4
Mazin Karjikar
commited on
fix styling bug
090e2ae
Daniel Nichols
commited on
initial commit
8ab167c
Daniel Nichols
commited on