Merge pull request #34 from winglian/v2-fixes
fixes for most recent update
This commit is contained in:
commit
b5e3dae573
|
|
@ -1,6 +1,6 @@
|
||||||
import torch
|
import torch
|
||||||
import numpy as np
|
import numpy as np
|
||||||
import quant_cuda
|
from gptq_llama import quant_cuda
|
||||||
|
|
||||||
|
|
||||||
# Global Buffer
|
# Global Buffer
|
||||||
|
|
|
||||||
|
|
@ -3,6 +3,7 @@ accelerate
|
||||||
bitsandbytes
|
bitsandbytes
|
||||||
datasets
|
datasets
|
||||||
sentencepiece
|
sentencepiece
|
||||||
|
safetensors
|
||||||
git+https://github.com/huggingface/transformers.git
|
git+https://github.com/huggingface/transformers.git
|
||||||
git+https://github.com/sterlind/GPTQ-for-LLaMa.git@lora_4bit
|
git+https://github.com/sterlind/GPTQ-for-LLaMa.git@lora_4bit
|
||||||
git+https://github.com/sterlind/peft.git
|
git+https://github.com/sterlind/peft.git
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue