RichardErkhov
commited on
Commit
•
3a91067
1
Parent(s):
5e00827
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
pygmalion-1.3b - GGUF
|
11 |
+
- Model creator: https://huggingface.co/PygmalionAI/
|
12 |
+
- Original model: https://huggingface.co/PygmalionAI/pygmalion-1.3b/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [pygmalion-1.3b.Q2_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q2_K.gguf) | Q2_K | 0.53GB |
|
18 |
+
| [pygmalion-1.3b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_XS.gguf) | IQ3_XS | 0.59GB |
|
19 |
+
| [pygmalion-1.3b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_S.gguf) | IQ3_S | 0.61GB |
|
20 |
+
| [pygmalion-1.3b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_S.gguf) | Q3_K_S | 0.61GB |
|
21 |
+
| [pygmalion-1.3b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_M.gguf) | IQ3_M | 0.66GB |
|
22 |
+
| [pygmalion-1.3b.Q3_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K.gguf) | Q3_K | 0.71GB |
|
23 |
+
| [pygmalion-1.3b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_M.gguf) | Q3_K_M | 0.71GB |
|
24 |
+
| [pygmalion-1.3b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_L.gguf) | Q3_K_L | 0.77GB |
|
25 |
+
| [pygmalion-1.3b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_XS.gguf) | IQ4_XS | 0.74GB |
|
26 |
+
| [pygmalion-1.3b.Q4_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_0.gguf) | Q4_0 | 0.77GB |
|
27 |
+
| [pygmalion-1.3b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_NL.gguf) | IQ4_NL | 0.78GB |
|
28 |
+
| [pygmalion-1.3b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_S.gguf) | Q4_K_S | 0.78GB |
|
29 |
+
| [pygmalion-1.3b.Q4_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K.gguf) | Q4_K | 0.85GB |
|
30 |
+
| [pygmalion-1.3b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_M.gguf) | Q4_K_M | 0.85GB |
|
31 |
+
| [pygmalion-1.3b.Q4_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_1.gguf) | Q4_1 | 0.85GB |
|
32 |
+
| [pygmalion-1.3b.Q5_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_0.gguf) | Q5_0 | 0.92GB |
|
33 |
+
| [pygmalion-1.3b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_S.gguf) | Q5_K_S | 0.92GB |
|
34 |
+
| [pygmalion-1.3b.Q5_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K.gguf) | Q5_K | 0.98GB |
|
35 |
+
| [pygmalion-1.3b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_M.gguf) | Q5_K_M | 0.98GB |
|
36 |
+
| [pygmalion-1.3b.Q5_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_1.gguf) | Q5_1 | 1.0GB |
|
37 |
+
| [pygmalion-1.3b.Q6_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q6_K.gguf) | Q6_K | 1.08GB |
|
38 |
+
| [pygmalion-1.3b.Q8_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q8_0.gguf) | Q8_0 | 1.4GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
---
|
45 |
+
license: agpl-3.0
|
46 |
+
language:
|
47 |
+
- en
|
48 |
+
thumbnail:
|
49 |
+
tags:
|
50 |
+
- text generation
|
51 |
+
- conversational
|
52 |
+
inference: false
|
53 |
+
|
54 |
+
---
|
55 |
+
|
56 |
+
# Pygmalion 1.3B
|
57 |
+
|
58 |
+
## Model description
|
59 |
+
|
60 |
+
Pymalion 1.3B is a proof-of-concept dialogue model based on EleutherAI's [pythia-1.3b-deduped](https://huggingface.co/EleutherAI/pythia-1.3b-deduped).
|
61 |
+
|
62 |
+
**Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances.
|
63 |
+
|
64 |
+
## Training data
|
65 |
+
|
66 |
+
The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations.
|
67 |
+
|
68 |
+
## Training procedure
|
69 |
+
|
70 |
+
Fine-tuning was done using [ColossalAI](https://github.com/hpcaitech/ColossalAI) (specifically, with a slightly modified version of their [OPT fine-tune example](https://github.com/hpcaitech/ColossalAI/blob/78509124d32b63b7fc36f6508e0576a326d51422/examples/language/opt/run_clm.py)) for around 11.4 million tokens over 5440 steps on a single 24GB GPU. The run took just under 21 hours.
|
71 |
+
|
72 |
+
## Intended use
|
73 |
+
|
74 |
+
### The easy way
|
75 |
+
|
76 |
+
We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb).
|
77 |
+
|
78 |
+
### The manual way
|
79 |
+
|
80 |
+
The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:
|
81 |
+
|
82 |
+
```
|
83 |
+
[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
|
84 |
+
|
85 |
+
[DIALOGUE HISTORY]
|
86 |
+
You: [Your input message here]
|
87 |
+
[CHARACTER]:
|
88 |
+
```
|
89 |
+
|
90 |
+
Where `[CHARACTER] `is, as you can probably guess, the name of the character you want the model to portray, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:
|
91 |
+
|
92 |
+
```
|
93 |
+
[CHARACTER]: [some dialogue here]
|
94 |
+
You: [your response to the dialogue above]
|
95 |
+
```
|
96 |
+
|
97 |
+
Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.
|
98 |
+
|
99 |
+
## Known issues
|
100 |
+
|
101 |
+
- The model can get stuck repeating certain phrases, or sometimes even entire sentences.
|
102 |
+
- We believe this is due to that behavior being present in the training data itself, and plan to investigate and adjust accordingly for future versions.
|
103 |
+
|
104 |
+
|