Re-done GPTQ, quantised with sequence length 8K
Browse files
README.md
CHANGED
|
@@ -70,14 +70,14 @@ Each separate quant is in a different branch. See below for instructions on fet
|
|
| 70 |
|
| 71 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
| 72 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
| 73 |
-
| 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. |
|
| 74 |
-
| 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. |
|
| 75 |
-
| 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. |
|
| 76 |
-
| 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 than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
|
| 77 |
-
| gptq-8bit--1g-actorder_True | 8 | None | True | 13.36 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
|
| 78 |
-
| gptq-8bit-128g-actorder_False | 8 | 128 | False | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
|
| 79 |
-
| gptq-8bit-128g-actorder_True | 8 | 128 | True | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
|
| 80 |
-
| gptq-8bit-64g-actorder_True | 8 | 64 | True | 13.95 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
|
| 81 |
|
| 82 |
## How to download from branches
|
| 83 |
|
|
|
|
| 70 |
|
| 71 |
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
|
| 72 |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
|
| 73 |
+
| [main](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/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. |
|
| 74 |
+
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/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. |
|
| 75 |
+
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/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. |
|
| 76 |
+
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/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 than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
|
| 77 |
+
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | True | 13.36 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
|
| 78 |
+
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | False | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
|
| 79 |
+
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | True | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
|
| 80 |
+
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/OpenAssistant-Llama2-13B-Orca-8K-3319-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | True | 13.95 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
|
| 81 |
|
| 82 |
## How to download from branches
|
| 83 |
|