TheBloke commited on
Commit
449b7ef
1 Parent(s): 5341410

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -139,13 +139,13 @@ Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with T
139
 
140
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
141
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
142
- | [main](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 18.60 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
143
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 19.25 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
144
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 21.21 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
145
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 15.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
146
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 35.34 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
147
- | [gptq-3bit-32g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-3bit-32g-actorder_True) | 3 | 32 | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 16.90 GB | No | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. |
148
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 36.11 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
149
 
150
  <!-- README_GPTQ.md-provided-files end -->
151
 
 
139
 
140
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
141
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
142
+ | [main](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 18.60 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
143
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 19.25 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
144
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 21.21 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
145
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 15.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
146
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 35.34 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
147
+ | [gptq-3bit-32g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-3bit-32g-actorder_True) | 3 | 32 | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 16.90 GB | No | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. |
148
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Yi-34B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMWare Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 36.11 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
149
 
150
  <!-- README_GPTQ.md-provided-files end -->
151