Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ This is the GPTQ 4Bit Groupsize 128 Pre-Quantized Model, for the full model in f
|
|
5 |
|
6 |
As a base model used https://huggingface.co/eachadea/vicuna-13b-1.1
|
7 |
|
8 |
-
Finetuned on Teknium's GPTeacher dataset, unreleased Roleplay v2 dataset, GPT-4-LLM
|
9 |
|
10 |
Approx 180k instructions, all from GPT-4, all cleaned of any OpenAI censorship/"As an AI Language Model" etc.
|
11 |
|
@@ -13,6 +13,25 @@ Base model still has OpenAI censorship. Soon, a new version will be released wit
|
|
13 |
|
14 |
Trained on 8 A100-80GB GPUs for 5 epochs following Alpaca deepspeed training code.
|
15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
Nous Research Instruct Dataset will be released soon.
|
17 |
|
18 |
GPTeacher, Roleplay v2 by https://huggingface.co/teknium
|
|
|
5 |
|
6 |
As a base model used https://huggingface.co/eachadea/vicuna-13b-1.1
|
7 |
|
8 |
+
Finetuned on Teknium's GPTeacher dataset, Teknium's unreleased Roleplay v2 dataset, WizardLM Uncensored, GPT-4-LLM Uncensored, and Nous Research Instruct Dataset
|
9 |
|
10 |
Approx 180k instructions, all from GPT-4, all cleaned of any OpenAI censorship/"As an AI Language Model" etc.
|
11 |
|
|
|
13 |
|
14 |
Trained on 8 A100-80GB GPUs for 5 epochs following Alpaca deepspeed training code.
|
15 |
|
16 |
+
Prompt format is Alpaca:
|
17 |
+
```
|
18 |
+
### Instruction:
|
19 |
+
|
20 |
+
### Response:
|
21 |
+
```
|
22 |
+
|
23 |
+
or
|
24 |
+
|
25 |
+
```
|
26 |
+
### Instruction:
|
27 |
+
|
28 |
+
### Input:
|
29 |
+
|
30 |
+
### Response:
|
31 |
+
|
32 |
+
```
|
33 |
+
|
34 |
+
|
35 |
Nous Research Instruct Dataset will be released soon.
|
36 |
|
37 |
GPTeacher, Roleplay v2 by https://huggingface.co/teknium
|