Text Generation
Transformers
Safetensors
English
llama
conversational
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
6ec2419
1 Parent(s): 8285322

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -122,10 +122,12 @@ Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with T
122
 
123
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
124
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
125
- | [main](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 61.04 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
126
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 63.36 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
127
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 46.07 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
128
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.26 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
 
 
129
 
130
  <!-- README_GPTQ.md-provided-files end -->
131
 
 
122
 
123
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
124
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
125
+ | [main](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.99 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
126
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.91 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
127
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 46.07 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
128
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.26 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
129
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.87 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
130
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/MegaDolphin-120b-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 48.87 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
131
 
132
  <!-- README_GPTQ.md-provided-files end -->
133