---
license: llama2
language: en
commercial: 'no'
inference: false
quantized_by: shadowsword
model_creator: KoboldAI
model_link: https://huggingface.co/KoboldAI/LLAMA2-13B-Holodeck-1
model_name: LLAMA2 13B Holodeck 1
model_type: llama
pipeline_tag: text-generation
---
# Q4_K and Q5_K of LLAMA2 13B Holodeck 1
<!-- header start -->
<div style="width: 100%;">
    <img src="https://huggingface.co/spaces/shadowsword/misc/resolve/main/huggingface_shadowsword_kquant.png" alt="Shadowsword K-Quant Reuploads" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<!-- header end -->

a K-Quant re-upload by Shadowsword

https://huggingface.co/KoboldAI/LLAMA2-13B-Holodeck-1

ggmlv3 from TheBloke's make-ggml.py commit to huggingface repo

```bash
example$ python3 ./make-ggml.py --model /media/inpw/b28b0629-039b-47cc-b3ae-2e617ad16aea/LLAMA2-13B-Holodeck-1 --outname LLAMA2-13B-Holodeck-1 --outdir /media/inpw/b28b0629-039b-47cc-b3ae-2e617ad16aea/LLAMA2-13B-Holodeck-1 --quants Q4_K Q5_K
```

There are no changes to this KoboldAI/LLAMA2-13B-Holodeck-1 besides using the new ggmlv3 K-Quant method.

Original Card:

# LLAMA2 13B - Holodeck
## Model Description
LLAMA2 13B-Holodeck is a finetune created using Meta's llama 2 model.
## Training data
The training data contains around 3000 ebooks in various genres.
Most parts of the dataset have been prepended using the following text: `[Genre: <genre1>, <genre2>]`
### How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
```py
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/LLAMA2-13B-Holodeck-1')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt's all right," Janeway said. "I'm certain that you're doing your best to keep me informed of what\'s going on."'}]
```
### Limitations and Biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).

### License
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.

**Extra clause:**
You shall use the Materials and Products solely for research purposes or personal use and not for any commercial purpose. Nothing in the Community License shall be construed as granting you a license to use the Materials or Products for any other purpose.

### BibTeX entry and citation info
https://huggingface.co/meta-llama/Llama-2-13b-hf