TheBloke commited on
Commit
d015905
1 Parent(s): 2e2dc08

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -62,8 +62,8 @@ Each separate quant is in a different branch. See below for instructions on fet
62
  | gptq-4bit-32g-actorder_True | 4 | 32 | True | Processing, coming soon | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
63
  | gptq-4bit-64g-actorder_True | 4 | 64 | True | 37.99 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. |
64
  | gptq-4bit-128g-actorder_True | 4 | 128 | True | Processing, coming soon | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
65
- | gptq-3bit--1g-actorder_True | 3 | None | True | Processing, coming soon | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
66
- | gptq-3bit-128g-actorder_False | 3 | 128 | False | Processing, coming soon | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
67
  | gptq-3bit-128g-actorder_True | 3 | 128 | True | Processing, coming soon | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
68
  | gptq-3bit-64g-actorder_True | 3 | 64 | True | Processing, coming soon | False | AutoGPTQ | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. Poor AutoGPTQ CUDA speed. |
69
 
 
62
  | gptq-4bit-32g-actorder_True | 4 | 32 | True | Processing, coming soon | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
63
  | gptq-4bit-64g-actorder_True | 4 | 64 | True | 37.99 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. |
64
  | gptq-4bit-128g-actorder_True | 4 | 128 | True | Processing, coming soon | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
65
+ | gptq-3bit--1g-actorder_True | 3 | None | True | 26.78 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
66
+ | gptq-3bit-128g-actorder_False | 3 | 128 | False | 28.03 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
67
  | gptq-3bit-128g-actorder_True | 3 | 128 | True | Processing, coming soon | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
68
  | gptq-3bit-64g-actorder_True | 3 | 64 | True | Processing, coming soon | False | AutoGPTQ | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. Poor AutoGPTQ CUDA speed. |
69