Update README.md
Browse files
README.md
CHANGED
@@ -63,7 +63,7 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
63 |
|
64 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
65 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
66 |
-
| main | 4 |
|
67 |
| gptq-4bit-128g-actorder_False | 4 | 128 | False | 36.65 GB | True | AutoGPTQ | 4-bit, without Act Order and group size 128g. |
|
68 |
| 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. |
|
69 |
| 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. |
|
|
|
63 |
|
64 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
65 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
66 |
+
| main | 4 | 128g | False | - GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
|
67 |
| gptq-4bit-128g-actorder_False | 4 | 128 | False | 36.65 GB | True | AutoGPTQ | 4-bit, without Act Order and group size 128g. |
|
68 |
| 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. |
|
69 |
| 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. |
|