File size: 10,853 Bytes
2ae62b5 366a80c 2ae62b5 366a80c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
---
base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
- zh
- ko
- ja
license: llama3.1
pipeline_tag: text-generation
tags:
- roleplay
- llama3
- sillytavern
- idol
- facebook
- meta
- pytorch
- llama
- llama-3
quantized_by: bartowski
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
---
## Llamacpp imatrix Quantizations of DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3496">b3496</a> for quantization.
Original model: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
<|eot_id|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-f32.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-f32.gguf) | f32 | 32.13GB | false | Full F32 weights. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6_K_L.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6_K.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_L.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_M.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_S.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_L.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_M.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for must use cases, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_XL.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_S.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ4_XS.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_L.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_M.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3_M.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2_K_L.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_S.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3_XS.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2_K.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ2_M.gguf](https://huggingface.co/bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF/blob/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-IQ2_M.gguf) | IQ2_M | 2.95GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
Thank you ZeroWw for the inspiration to experiment with embed/output
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF --include "DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF --include "DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|