玩模型开放模型 · 清晰来源 · 自主选择
返回模型目录
bartowski /

Lexi-Llama-3-8B-Uncensored-exl2

HF 源站

bartowski/Lexi-Llama-3-8B-Uncensored-exl2 is an uncensored open-source model hosted on Hugging Face.

Text GenerationLicense: llama38Buncensoredinstructopen
README.md说明 / 使用方法

license: llama3 tags:

  • uncensored
  • llama3
  • instruct
  • open quantized_by: bartowski pipeline_tag: text-generation

Exllama v2 Quantizations of Lexi-Llama-3-8B-Uncensored

If generation refuses to stop, you can edit tokenizer_config.json.

Replace line 2055:

"eos_token": "<|end_of_text|>",

with:

"eos_token": "<|eot_id|>",

Using turboderp's ExLlamaV2 v0.0.19 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored

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|>


Available sizes

BranchBitslm_head bitsVRAM (4k)VRAM (8K)VRAM (16k)VRAM (32k)Description
8_08.08.010.1 GB10.5 GB11.5 GB13.6 GBMaximum quality that ExLlamaV2 can produce, near unquantized performance.
6_56.58.08.9 GB9.3 GB10.3 GB12.4 GBVery similar to 8.0, good tradeoff of size vs performance, recommended.
5_05.06.07.7 GB8.1 GB9.1 GB11.2 GBSlightly lower quality vs 6.5, but usable on 8GB cards.
4_254.256.07.0 GB7.4 GB8.4 GB10.5 GBGPTQ equivalent bits per weight, slightly higher quality.
3_53.56.06.4 GB6.8 GB7.8 GB9.9 GBLower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Lexi-Llama-3-8B-Uncensored-exl2 Lexi-Llama-3-8B-Uncensored-exl2-6_5

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:

Linux:

huggingface-cli download bartowski/Lexi-Llama-3-8B-Uncensored-exl2 --revision 6_5 --local-dir Lexi-Llama-3-8B-Uncensored-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download bartowski/Lexi-Llama-3-8B-Uncensored-exl2 --revision 6_5 --local-dir Lexi-Llama-3-8B-Uncensored-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

HUGGING FACE

上游数据

HF 下载量10
HF 点赞量3

HF 下载量为源站最近 30 天统计,与本站点击分开。

SITE STATS

本站统计

下载点击—
请求数—
匿名去重—最近 7 天—

本站下载量记录按钮点击,不代表下载完成;短时连点会去重。

来源与版本

作者
bartowski
最近更新
2024/04/24
最新创建
2024/04/24
HF 趋势
未知
数据快照
2026/09/16
版本
未知
许可证
llama3