 oobabooga
|
e9dbdafb14
Merge branch 'main' into pt-path-changes
|
2 years ago |
|
oobabooga
|
706a03b2cb
Minor changes
|
2 years ago |
|
oobabooga
|
de7dd8b6aa
Add comments
|
2 years ago |
|
oobabooga
|
e461c0b7a0
Move the import to the top
|
2 years ago |
 deepdiffuser
|
9fbd60bf22
add no_split_module_classes to prevent tensor split error
|
2 years ago |
|
deepdiffuser
|
ab47044459
add multi-gpu support for 4bit gptq LLaMA
|
2 years ago |
 rohvani
|
2ac2913747
fix reference issue
|
2 years ago |
|
rohvani
|
826e297b0e
add llama-65b-4bit support & multiple pt paths
|
2 years ago |
|
oobabooga
|
9849aac0f1
Don't show .pt models in the list
|
2 years ago |
|
oobabooga
|
74102d5ee4
Insert to the path instead of appending
|
2 years ago |
|
oobabooga
|
2965aa1625
Check if the .pt file exists
|
2 years ago |
|
oobabooga
|
828a524f9a
Add LLaMA 4-bit support
|
2 years ago |
|
oobabooga
|
e91f4bc25a
Add RWKV tokenizer
|
2 years ago |
|
oobabooga
|
c33715ad5b
Move towards HF LLaMA implementation
|
2 years ago |
|
oobabooga
|
bd8aac8fa4
Add LLaMA 8-bit support
|
2 years ago |
|
oobabooga
|
ed8b35efd2
Add --pin-weight parameter for FlexGen
|
2 years ago |
|
oobabooga
|
ea5c5eb3da
Add LLaMA support
|
2 years ago |
|
oobabooga
|
659bb76722
Add RWKVModel class
|
2 years ago |
|
oobabooga
|
6837d4d72a
Load the model by name
|
2 years ago |
|
oobabooga
|
70e522732c
Move RWKV loader into a separate file
|
2 years ago |
|
oobabooga
|
ebc64a408c
RWKV support prototype
|
2 years ago |
|
oobabooga
|
8e3e8a070f
Make FlexGen work with the newest API
|
2 years ago |
|
oobabooga
|
65326b545a
Move all gradio elements to shared (so that extensions can use them)
|
2 years ago |
|
oobabooga
|
f6f792363b
Separate command-line params by spaces instead of commas
|
2 years ago |
 luis
|
5abdc99a7c
gpu-memory arg change
|
2 years ago |
|
oobabooga
|
7224343a70
Improve the imports
|
2 years ago |
|
oobabooga
|
e46c43afa6
Move some stuff from server.py to modules
|
2 years ago |
|
oobabooga
|
1dacd34165
Further refactor
|
2 years ago |
