Initial
Browse files
README.md
CHANGED
@@ -1,3 +1,50 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
This is a llama-13B based model that has been converted with GPTQ to 4bit quantized model.
|
5 |
+
|
6 |
+
Base Model: GPT4-x-Alpaca full fine tune by Chavinlo -> https://huggingface.co/chavinlo/gpt4-x-alpaca
|
7 |
+
LORA fine tune using the Roleplay Instruct from GPT4 generated dataset -> https://github.com/teknium1/GPTeacher/tree/main/Roleplay
|
8 |
+
LORA Adapter Only: https://huggingface.co/ZeusLabs/gpt4-x-alpaca-rp-lora - The v2 one -
|
9 |
+
|
10 |
+
Merged LORA to the model.
|
11 |
+
|
12 |
+
FYI Latest HF Transformers generates BROKEN generations.
|
13 |
+
Try this instead if your generations are terrible (first uninstall transformers): pip install git+https://github.com/huggingface/transformers@9eae4aa57650c1dbe1becd4e0979f6ad1e572ac0
|
14 |
+
More info and possible alternative solutions in these github issues.
|
15 |
+
https://github.com/tloen/alpaca-lora/issues/279#issuecomment-1514725886
|
16 |
+
https://github.com/oobabooga/text-generation-webui/issues/931#issuecomment-1516215250
|
17 |
+
|
18 |
+
Instructions simply using alpaca format are likely to be of lower quality. If you want pure general instruct capability I reccomend GPT-4-X-Alpaca (the base model of this) -
|
19 |
+
The model responds well to giving it a roleplay task in the preprompt, and the actual conversation in the "### Input: " field.
|
20 |
+
|
21 |
+
For a better idea of prompting it for roleplay, check out the roleplay discord bot code I made here: https://github.com/teknium1/alpaca-roleplay-discordbot
|
22 |
+
Here is an example:
|
23 |
+
```
|
24 |
+
### Instruction:
|
25 |
+
Role play as character that is described in the following lines. You always stay in character.
|
26 |
+
{"Your name is " + name + "." if name else ""}
|
27 |
+
{"Your backstory and history are: " + background if background else ""}
|
28 |
+
{"Your personality is: " + personality if personality else ""}
|
29 |
+
{"Your current circumstances and situation are: " + circumstances if circumstances else ""}
|
30 |
+
{"Your common greetings are: " + common_greeting if common_greeting else ""}
|
31 |
+
Remember, you always stay on character. You are the character described above.
|
32 |
+
{past_dialogue_formatted}
|
33 |
+
{chat_history if chat_history else "Chatbot: Hello!"}
|
34 |
+
|
35 |
+
Always speak with new and unique messages that haven't been said in the chat history.
|
36 |
+
|
37 |
+
Respond to this message as your character would:
|
38 |
+
### Input:
|
39 |
+
{text}
|
40 |
+
### Response:
|
41 |
+
{name}:
|
42 |
+
|
43 |
+
```
|
44 |
+
|
45 |
+
---
|
46 |
+
tags:
|
47 |
+
- llama
|
48 |
+
- alpaca
|
49 |
+
- gpt4
|
50 |
+
---
|