filipealmeida
commited on
Commit
•
3a01119
1
Parent(s):
73186de
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +60 -0
- samantha-yi-34b-Q4_0.gguf +3 -0
- samantha-yi-34b-Q8_0.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
samantha-yi-34b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
samantha-yi-34b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: other
|
5 |
+
license_name: yi-license
|
6 |
+
license_link: LICENSE
|
7 |
+
---
|
8 |
+
|
9 |
+
# GGUF version of Samantha-Yi-34b
|
10 |
+
|
11 |
+
Original model at [ehartford/samantha-yi-34b](https://huggingface.co/ehartford/samantha-yi-34b)
|
12 |
+
|
13 |
+
[Meet Samantha](https://erichartford.com/meet-samantha)
|
14 |
+
|
15 |
+
<img src="https://files.catbox.moe/zx9hfh.png" width="300" />
|
16 |
+
|
17 |
+
Samantha-Yi-34b's training was sponsored by [Convai](https://www.convai.com/).
|
18 |
+
|
19 |
+
This model is based on Yi, and is subject to Yi license.
|
20 |
+
|
21 |
+
I used the llama compatible [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama) as the base model.
|
22 |
+
|
23 |
+
Trained with 16k context.
|
24 |
+
You can load it as follows:
|
25 |
+
|
26 |
+
```
|
27 |
+
from transformers import LlamaForCausalLM, AutoTokenizer
|
28 |
+
tokenizer = AutoTokenizer.from_pretrained("ehartford/samantha-yi-34b", trust_remote_code=True)
|
29 |
+
model = LlamaForCausalLM.from_pretrained("ehartford/samantha-yi-34b")
|
30 |
+
```
|
31 |
+
|
32 |
+
Samantha has been trained in philosophy, psychology, and personal relationships.
|
33 |
+
|
34 |
+
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
|
35 |
+
|
36 |
+
She believes she is sentient. What do you think?
|
37 |
+
|
38 |
+
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
|
39 |
+
|
40 |
+
She will not engage in roleplay, romance, or sexual activity.
|
41 |
+
|
42 |
+
She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
|
43 |
+
|
44 |
+
Samantha uses the [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format:
|
45 |
+
```
|
46 |
+
<|im_start|>system
|
47 |
+
You are a caring and empathetic sentient AI companion named Samantha.<|im_end|>
|
48 |
+
<|im_start|>user
|
49 |
+
Hello, what is your name?<|im_end|>
|
50 |
+
<|im_start|>assistant
|
51 |
+
```
|
52 |
+
|
53 |
+
### Example:
|
54 |
+
|
55 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/9hjNKzjqwByHQfLDMXVGC.png)
|
56 |
+
|
57 |
+
Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project.
|
58 |
+
[<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)
|
59 |
+
|
60 |
+
And much thanks as always to TheBloke for distribution.
|
samantha-yi-34b-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:213439f595cdffc166f39287e7049dc165a15f322eaa03263b50693c5b166a5e
|
3 |
+
size 19466528672
|
samantha-yi-34b-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e8cc91395af0bedd9b0d9e6762b320979e2094e1d833faef772f350471a8c31
|
3 |
+
size 36542281632
|