Update README.md
Browse files
README.md
CHANGED
@@ -55,13 +55,13 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
55 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
56 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
57 |
| main | 4 | None | True | 35.33 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
|
58 |
-
| gptq-4bit-32g-actorder_True | 4 | 32 | True |
|
59 |
| 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. |
|
60 |
| gptq-4bit-128g-actorder_True | 4 | 128 | True | 36.65 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. |
|
61 |
-
| gptq-3bit--1g-actorder_True | 3 | None | True |
|
62 |
-
| gptq-3bit-128g-actorder_False | 3 | 128 | False |
|
63 |
-
| gptq-3bit-128g-actorder_True | 3 | 128 | True |
|
64 |
-
| gptq-3bit-64g-actorder_True | 3 | 64 | True |
|
65 |
|
66 |
## How to download from branches
|
67 |
|
|
|
55 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
56 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
57 |
| main | 4 | None | True | 35.33 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
|
58 |
+
| gptq-4bit-32g-actorder_True | 4 | 32 | True | Still processing | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
|
59 |
| 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. |
|
60 |
| gptq-4bit-128g-actorder_True | 4 | 128 | True | 36.65 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. |
|
61 |
+
| gptq-3bit--1g-actorder_True | 3 | None | True | Still processing | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
|
62 |
+
| gptq-3bit-128g-actorder_False | 3 | 128 | False | Still processing | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
|
63 |
+
| gptq-3bit-128g-actorder_True | 3 | 128 | True | Still processing | False | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
|
64 |
+
| gptq-3bit-64g-actorder_True | 3 | 64 | True | Still processing | False | AutoGPTQ | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. Poor AutoGPTQ CUDA speed. |
|
65 |
|
66 |
## How to download from branches
|
67 |
|