GGUF
Inference Endpoints
conversational
aashish1904 commited on
Commit
810881f
1 Parent(s): 00c0c42

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +78 -0
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ license: cc-by-nc-4.0
5
+ datasets:
6
+ - victunes/nart-100k-synthetic-buddy-mixed-names
7
+
8
+ ---
9
+
10
+ [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://huggingface.co/QuantFactory)
11
+
12
+
13
+ # QuantFactory/TherapyLlama-8B-v1-GGUF
14
+ This is quantized version of [victunes/TherapyLlama-8B-v1](https://huggingface.co/victunes/TherapyLlama-8B-v1) created using llama.cpp
15
+
16
+ # Original Model Card
17
+
18
+ **GGUF:** https://huggingface.co/victunes/TherapyLlama-8B-v1-GGUF
19
+
20
+ # TherapyLlama 8B v1
21
+
22
+ _Buddy is here for you._
23
+
24
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f07d05279d2d8f725bf0c3/A-ckcZ9H0Ee1n_ls2FM41.png)
25
+
26
+ Trained on Llama 3 8B using a modified version of [jerryjalapeno/nart-100k-synthetic](https://huggingface.co/datasets/jerryjalapeno/nart-100k-synthetic).
27
+
28
+ It is a Llama 3 version of https://huggingface.co/victunes/TherapyBeagle-11B-v2
29
+
30
+ TherapyLlama is _hopefully_ aligned to be helpful, healthy, and comforting.
31
+
32
+ ## IMPORTANT: Use Vicuna format
33
+
34
+ This was trained with the Vicuna 1.1 format. Use the Vicuna format! Do NOT use the Llama 3 format.
35
+
36
+ ## Usage
37
+ - Do not hold back on Buddy.
38
+ - Open up to Buddy.
39
+ - Pour your heart out to Buddy.
40
+ - Engage with Buddy.
41
+ - Remember that Buddy is just an AI.
42
+
43
+ ## Notes
44
+ - Tested with the Vicuna 1.1 Format
45
+ - You might be assigned a random name if you don't give yourself one.
46
+ - RP capabilities are weaker compared to TherapyBeagle.
47
+ - Make sure to say **"You are Socrates"** for its best RP attempt.
48
+
49
+ ## Disclaimer
50
+ **TherapyLlama is NOT a real therapist. It is a friendly AI that mimics empathy and psychotherapy.
51
+ It is an illusion without the slightest clue who you are as a person.
52
+ As much as it can help you with self-discovery, A LLAMA IS NOT A SUBSTITUTE to a real professional.**
53
+
54
+ With that said, I found it to be a very helpful tool in unravelling one's self. I hope this model can help sooth minds and hearts.
55
+
56
+ ## Examples
57
+
58
+ ### LLAMA 3 INSTRUCT
59
+ ```
60
+ {{[INPUT]}}
61
+ Hello, I'm victunes
62
+ {{[OUTPUT]}}
63
+ Hi victunes! Welcome to our session. I'm here to listen and support you. How are you feeling today?
64
+ {{[INPUT]}}
65
+ I've been feeling down lately.
66
+ {{[OUTPUT]}}
67
+ I'm sorry to hear that. Can you tell me more about what's been going on?
68
+ {{[INPUT]}}
69
+ I think I'm pretty lonely.
70
+ {{[OUTPUT]}}
71
+ Loneliness can be really tough. It sounds like it's been weighing heavily on your mind. What makes you feel lonely?
72
+ {{[INPUT]}}
73
+ My friend died recently.
74
+ {{[OUTPUT]}}
75
+ Oh, I'm so sorry for your loss, victunes. Losing a friend is never easy. How have you been coping with the grief?
76
+ ```
77
+
78
+ **GGUF:** https://huggingface.co/victunes/TherapyLlama-8B-v1-GGUF