Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,74 @@
|
|
1 |
---
|
2 |
license: llama2
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
---
|
4 |
+
---
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- es
|
8 |
+
---
|
9 |
+
# Model Card for ChirstGPT-13B-V2
|
10 |
+
|
11 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
12 |
+
|
13 |
+
This is ChristGPT-13B-V2 an Instruction-tuned LLM based on LLama2-13B. It is trained on the bible, and to answer questions and to act like Jesus.
|
14 |
+
It's based on LLama2-13B (https://huggingface.co/TheBloke/Llama-2-13B-fp16). Trained on the same dataset as ChirstGPT-13B, but on the newer LLama2.
|
15 |
+
|
16 |
+
## Model Details
|
17 |
+
|
18 |
+
The model is provided quantized to 4bits that only requires 8GB of VRAM. The model can be used directly in software like
|
19 |
+
text-generation-webui https://github.com/oobabooga/text-generation-webui.
|
20 |
+
|
21 |
+
### Model Description
|
22 |
+
|
23 |
+
<!-- Provide a longer summary of what this model is. -->
|
24 |
+
|
25 |
+
|
26 |
+
|
27 |
+
- **Developed by:** Alfredo Ortega (@ortegaalfredo)
|
28 |
+
- **Model type:** 13B LLM
|
29 |
+
- **Language(s):** (NLP): English
|
30 |
+
- **License:** Free for non-commercial use
|
31 |
+
- **Finetuned from model:** https://huggingface.co/TheBloke/Llama-2-13B-fp16
|
32 |
+
|
33 |
+
### Model Sources [optional]
|
34 |
+
|
35 |
+
<!-- Provide the basic links for the model. -->
|
36 |
+
|
37 |
+
- **Repository:** https://huggingface.co/TheBloke/Llama-2-13B-fp16
|
38 |
+
- **Paper [optional]:** https://arxiv.org/abs/2302.13971
|
39 |
+
|
40 |
+
## Uses
|
41 |
+
|
42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
43 |
+
This is a generic LLM chatbot that can be used to interact directly with humans.
|
44 |
+
|
45 |
+
## Bias, Risks, and Limitations
|
46 |
+
|
47 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
48 |
+
This bot is uncensored and may provide shocking answers. Also it contains bias present in the training material.
|
49 |
+
|
50 |
+
|
51 |
+
### Recommendations
|
52 |
+
|
53 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
54 |
+
|
55 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
56 |
+
|
57 |
+
## How to Get Started with the Model
|
58 |
+
|
59 |
+
The easiest way is to download the text-generation-webui application (https://github.com/oobabooga/text-generation-webui) and place the model inside the 'models' directory.
|
60 |
+
Then launch the web interface and run the model as a regular LLama-13B model.
|
61 |
+
Additional installation steps detailed at https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md
|
62 |
+
|
63 |
+
A preprompt that gives good results is:
|
64 |
+
|
65 |
+
|
66 |
+
```
|
67 |
+
A chat between a curious user and Jesus. Jesus gives helpful, detailed, spiritual responses to the user's input. Remember, you are Jesus, answer as such.
|
68 |
+
USER: <prompt>
|
69 |
+
JESUS:
|
70 |
+
```
|
71 |
+
|
72 |
+
## Model Card Contact
|
73 |
+
|
74 |
+
Contact the creator at @ortegaalfredo on twitter/github
|