RichardErkhov
commited on
Commit
•
9e5b531
1
Parent(s):
06f3b35
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
harry_potter_chatbot - GGUF
|
11 |
+
- Model creator: https://huggingface.co/diabolic6045/
|
12 |
+
- Original model: https://huggingface.co/diabolic6045/harry_potter_chatbot/
|
13 |
+
|
14 |
+
|
15 |
+
| Name | Quant method | Size |
|
16 |
+
| ---- | ---- | ---- |
|
17 |
+
| [harry_potter_chatbot.Q2_K.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q2_K.gguf) | Q2_K | 0.17GB |
|
18 |
+
| [harry_potter_chatbot.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.IQ3_XS.gguf) | IQ3_XS | 0.18GB |
|
19 |
+
| [harry_potter_chatbot.IQ3_S.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.IQ3_S.gguf) | IQ3_S | 0.19GB |
|
20 |
+
| [harry_potter_chatbot.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q3_K_S.gguf) | Q3_K_S | 0.19GB |
|
21 |
+
| [harry_potter_chatbot.IQ3_M.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.IQ3_M.gguf) | IQ3_M | 0.2GB |
|
22 |
+
| [harry_potter_chatbot.Q3_K.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q3_K.gguf) | Q3_K | 0.21GB |
|
23 |
+
| [harry_potter_chatbot.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q3_K_M.gguf) | Q3_K_M | 0.21GB |
|
24 |
+
| [harry_potter_chatbot.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q3_K_L.gguf) | Q3_K_L | 0.23GB |
|
25 |
+
| [harry_potter_chatbot.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.IQ4_XS.gguf) | IQ4_XS | 0.22GB |
|
26 |
+
| [harry_potter_chatbot.Q4_0.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q4_0.gguf) | Q4_0 | 0.23GB |
|
27 |
+
| [harry_potter_chatbot.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.IQ4_NL.gguf) | IQ4_NL | 0.23GB |
|
28 |
+
| [harry_potter_chatbot.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q4_K_S.gguf) | Q4_K_S | 0.23GB |
|
29 |
+
| [harry_potter_chatbot.Q4_K.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q4_K.gguf) | Q4_K | 0.25GB |
|
30 |
+
| [harry_potter_chatbot.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q4_K_M.gguf) | Q4_K_M | 0.25GB |
|
31 |
+
| [harry_potter_chatbot.Q4_1.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q4_1.gguf) | Q4_1 | 0.25GB |
|
32 |
+
| [harry_potter_chatbot.Q5_0.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q5_0.gguf) | Q5_0 | 0.27GB |
|
33 |
+
| [harry_potter_chatbot.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q5_K_S.gguf) | Q5_K_S | 0.27GB |
|
34 |
+
| [harry_potter_chatbot.Q5_K.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q5_K.gguf) | Q5_K | 0.29GB |
|
35 |
+
| [harry_potter_chatbot.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q5_K_M.gguf) | Q5_K_M | 0.29GB |
|
36 |
+
| [harry_potter_chatbot.Q5_1.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q5_1.gguf) | Q5_1 | 0.29GB |
|
37 |
+
| [harry_potter_chatbot.Q6_K.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q6_K.gguf) | Q6_K | 0.32GB |
|
38 |
+
| [harry_potter_chatbot.Q8_0.gguf](https://huggingface.co/RichardErkhov/diabolic6045_-_harry_potter_chatbot-gguf/blob/main/harry_potter_chatbot.Q8_0.gguf) | Q8_0 | 0.41GB |
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
Original model description:
|
44 |
+
# Harry Potter Chatbot
|
45 |
+
|
46 |
+
This model is a chatbot designed to generate responses in the style of Harry Potter, the protagonist from J.K. Rowling's popular book series and its movie adaptations.
|
47 |
+
|
48 |
+
## Model Architecture
|
49 |
+
|
50 |
+
The `harry_potter_chatbot` is based on the [`DialoGPT-medium`](https://huggingface.co/microsoft/DialoGPT-medium) model, a powerful GPT-based architecture designed for generating conversational responses. It has been fine-tuned on a dataset of Harry Potter's dialogues from movie transcripts.
|
51 |
+
|
52 |
+
## Usage
|
53 |
+
|
54 |
+
You can use this model to generate responses for a given input text using the following code:
|
55 |
+
|
56 |
+
```python
|
57 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
58 |
+
|
59 |
+
tokenizer = AutoTokenizer.from_pretrained("diabolic6045/harry_potter_chatbot")
|
60 |
+
model = AutoModelForCausalLM.from_pretrained("diabolic6045/harry_potter_chatbot")
|
61 |
+
|
62 |
+
input_text = "What's your favorite spell?"
|
63 |
+
input_tokens = tokenizer.encode(input_text, return_tensors='pt')
|
64 |
+
output_tokens = model.generate(input_tokens, max_length=50, num_return_sequences=1)
|
65 |
+
output_text = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
|
66 |
+
|
67 |
+
print(output_text)
|
68 |
+
```
|
69 |
+
|
70 |
+
## Limitations
|
71 |
+
|
72 |
+
This model is specifically designed to generate responses in the style of Harry Potter and may not provide accurate or coherent answers to general knowledge questions. It may also sometimes generate inappropriate responses. Be cautious while using this model in a public setting or for critical applications.
|
73 |
+
|
74 |
+
## Training Data
|
75 |
+
|
76 |
+
The model was fine-tuned on a dataset of Harry Potter's dialogues from movie transcripts. The dataset was collected from publicly available movie scripts and includes conversations and quotes from various Harry Potter films.
|
77 |
+
|
78 |
+
## Acknowledgments
|
79 |
+
|
80 |
+
This model was trained using the Hugging Face [Transformers](https://github.com/huggingface/transformers) library, and it is based on the [`DialoGPT-medium`](https://huggingface.co/microsoft/DialoGPT-medium) model by Microsoft. Special thanks to the Hugging Face team and Microsoft for their contributions to the NLP community.
|
81 |
+
|
82 |
+
---
|
83 |
+
|
84 |
+
Feel free to test the model and provide feedback or report any issues. Enjoy chatting with Harry Potter!
|
85 |
+
|
86 |
+
|