TheBloke commited on
Commit
06a7513
1 Parent(s): 4bc24d4

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -57,8 +57,8 @@ Each separate quant is in a different branch. See below for instructions on fet
57
  | ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
58
  | main | 4 | 128 | False | 7.26 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
59
  | gptq-4bit-32g-actorder_True | 4 | 32 | True | 8.00 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
60
- | gptq-4bit-64g-actorder_True | 4 | 64 | True | Still uploading | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
61
- | gptq-4bit-128g-actorder_True | 4 | 128 | True | Still uploading | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
62
 
63
  ## How to download from branches
64
 
 
57
  | ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
58
  | main | 4 | 128 | False | 7.26 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
59
  | gptq-4bit-32g-actorder_True | 4 | 32 | True | 8.00 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
60
+ | gptq-4bit-64g-actorder_True | 4 | 64 | True | 7.51 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
61
+ | gptq-4bit-128g-actorder_True | 4 | 128 | True | 7.26 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
62
 
63
  ## How to download from branches
64