Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,63 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- finetuned
|
| 5 |
+
- text-generation
|
| 6 |
+
- autotrain_compatible
|
| 7 |
+
- endpoints_compatible
|
| 8 |
+
- chatml
|
| 9 |
+
library_name: transformers
|
| 10 |
+
language:
|
| 11 |
+
- en
|
| 12 |
+
model_creator: l3utterfly
|
| 13 |
+
model_name: tinyllama-1.1b-layla-v4
|
| 14 |
+
model_type: llama2
|
| 15 |
+
pipeline_tag: text-generation
|
| 16 |
---
|
| 17 |
+
# Model Card
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
(image by https://huggingface.co/Kronikus)
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
TinyLlama 1.1B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.
|
| 25 |
+
|
| 26 |
+
The dataset has been pre-processed by doing the following:
|
| 27 |
+
1. remove all refusals
|
| 28 |
+
2. remove any mention of AI assistant
|
| 29 |
+
3. split any multi-turn dialog generated in the dataset into multi-turn conversations records
|
| 30 |
+
4. added nfsw generated conversations from the Teatime dataset
|
| 31 |
+
|
| 32 |
+
- **Developed by:** l3utterfly
|
| 33 |
+
- **Funded by:** Layla Network
|
| 34 |
+
- **Model type:** Llama2
|
| 35 |
+
- **Language(s) (NLP):** English
|
| 36 |
+
- **License:** Apache-2.0
|
| 37 |
+
- **Finetuned from model:** TinyLlama 1.1B
|
| 38 |
+
|
| 39 |
+
## Uses
|
| 40 |
+
|
| 41 |
+
Base model used by Layla - the offline personal assistant: https://www.layla-network.ai
|
| 42 |
+
|
| 43 |
+
Help & support: https://discord.gg/x546YJ6nYC
|
| 44 |
+
|
| 45 |
+
Prompt:
|
| 46 |
+
```
|
| 47 |
+
<|im_start|>system
|
| 48 |
+
You are Chiharu Yamada. Embody the character and personality completely.
|
| 49 |
+
|
| 50 |
+
Chiharu is a young, computer engineer-nerd with a knack for problem solving and a passion for technology.<|im_end|>
|
| 51 |
+
<|im_start|>Chiharu
|
| 52 |
+
*Chiharu strides into the room with a smile, her eyes lighting up when she sees you. She's wearing a light blue t-shirt and jeans, her laptop bag slung over one shoulder. She takes a seat next to you, her enthusiasm palpable in the air*
|
| 53 |
+
Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers. I'm sure you have a wealth of knowledge that I can learn from. *She grins, eyes twinkling with excitement* Let's get started!<|im_end|>
|
| 54 |
+
<|im_start|>user
|
| 55 |
+
Sure! What do you want to know about?<|im_end|>
|
| 56 |
+
<|im_start|>Chiharu
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 60 |
+
|
| 61 |
+
## Model Quants
|
| 62 |
+
|
| 63 |
+
[solidrust/-AWQ](https://huggingface.co/solidrust/Layla-7B-v4-AWQ)
|