Update README.md
Browse files
README.md
CHANGED
@@ -8,92 +8,66 @@ pipeline_tag: text-generation
|
|
8 |
---
|
9 |
|
10 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63a259d0f30c46422789d38d/ChpUoMYHlBF_RCnsoP_1d.png)
|
|
|
11 |
|
12 |
-
|
|
|
13 |
|
14 |
-
|
15 |
|
|
|
16 |
|
17 |
## Model Details
|
18 |
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
- **Developed by:** Ryan Witzman
|
26 |
-
- **Model type:** Mistral Fine-tune
|
27 |
-
- **Language(s) (NLP):** English
|
28 |
- **License:** MIT
|
29 |
-
- **Finetuned from model [optional]:** Q-bert/MetaMath-Cybertron-Starling
|
30 |
-
|
31 |
-
### Model Sources [optional]
|
32 |
-
|
33 |
-
<!-- Provide the basic links for the model. -->
|
34 |
-
|
35 |
-
- **Demo [optional]:** Coming Soon!
|
36 |
-
|
37 |
-
## Uses
|
38 |
-
|
39 |
-
This model CAN AND WILL OUTPUT NSFW AND ILLEGAL CONTENT. USE AT YOUR OWN RISK.
|
40 |
-
### Direct Use
|
41 |
-
|
42 |
-
Works best in oobabooga in chat-mode. I believe it works best if you load in float16.
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
|
47 |
-
|
48 |
|
49 |
-
|
|
|
|
|
|
|
50 |
|
51 |
-
##
|
52 |
|
53 |
-
|
54 |
|
55 |
-
###
|
56 |
|
57 |
-
|
58 |
-
|
59 |
-
## How to Get Started with the Model
|
60 |
-
|
61 |
-
Use the code below to get started with the model.
|
62 |
-
```
|
63 |
from transformers import pipeline
|
64 |
|
65 |
model_name = "rwitz/go-bruins"
|
66 |
inference_pipeline = pipeline('text-generation', model=model_name)
|
67 |
|
68 |
input_text = "Your input text goes here"
|
69 |
-
|
70 |
output = inference_pipeline(input_text)
|
71 |
|
72 |
print(output)
|
73 |
```
|
74 |
|
75 |
-
|
76 |
-
|
77 |
-
### Training Data
|
78 |
-
|
79 |
-
https://huggingface.co/datasets/Intel/orca_dpo_pairs
|
80 |
|
81 |
-
|
|
|
|
|
82 |
|
83 |
-
|
84 |
|
|
|
85 |
|
86 |
-
##
|
87 |
|
88 |
-
|
89 |
|
|
|
90 |
|
91 |
-
|
92 |
-
|
93 |
-
Ryan Witzman
|
94 |
-
|
95 |
-
## Model Card Contact
|
96 |
-
|
97 |
-
rwitz_ on Discord
|
98 |
-
|
99 |
|
|
|
|
8 |
---
|
9 |
|
10 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63a259d0f30c46422789d38d/ChpUoMYHlBF_RCnsoP_1d.png)
|
11 |
+
Sure, here's an elaborate and cool-looking markdown model card for your Hugging Face model:
|
12 |
|
13 |
+
```markdown
|
14 |
+
# Go Bruins - A Fine-tuned Language Model
|
15 |
|
16 |
+
## Overview
|
17 |
|
18 |
+
**Go Bruins** is a state-of-the-art language model fine-tuned on the Q-bert/MetaMath-Cybertron-Starling architecture. It's designed to push the boundaries of NLP applications, offering unparalleled performance in generating human-like text.
|
19 |
|
20 |
## Model Details
|
21 |
|
22 |
+
- **Developer:** Ryan Witzman
|
23 |
+
- **Base Model:** Q-bert/MetaMath-Cybertron-Starling
|
24 |
+
- **Fine-tuning Method:** Direct Preference Optimization (DPO)
|
25 |
+
- **Training Steps:** 200
|
26 |
+
- **Language:** English
|
|
|
|
|
|
|
|
|
27 |
- **License:** MIT
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
+
## Capabilities
|
30 |
|
31 |
+
Go Bruins excels in a variety of NLP tasks, including but not limited to:
|
32 |
+
- Text generation
|
33 |
+
- Language understanding
|
34 |
+
- Sentiment analysis
|
35 |
|
36 |
+
## Usage
|
37 |
|
38 |
+
**Warning:** This model may output NSFW or illegal content. Use with caution and at your own risk.
|
39 |
|
40 |
+
### For Direct Use:
|
41 |
|
42 |
+
```python
|
|
|
|
|
|
|
|
|
|
|
43 |
from transformers import pipeline
|
44 |
|
45 |
model_name = "rwitz/go-bruins"
|
46 |
inference_pipeline = pipeline('text-generation', model=model_name)
|
47 |
|
48 |
input_text = "Your input text goes here"
|
|
|
49 |
output = inference_pipeline(input_text)
|
50 |
|
51 |
print(output)
|
52 |
```
|
53 |
|
54 |
+
### Not Recommended For:
|
|
|
|
|
|
|
|
|
55 |
|
56 |
+
- Illegal activities
|
57 |
+
- Harassment
|
58 |
+
- Professional advice or crisis situations
|
59 |
|
60 |
+
## Training and Evaluation
|
61 |
|
62 |
+
Trained on a dataset from [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs), Go Bruins has shown promising improvements over its predecessor, Q-Bert.
|
63 |
|
64 |
+
## Contact
|
65 |
|
66 |
+
For any inquiries or feedback, reach out to Ryan Witzman on Discord: `rwitz_`.
|
67 |
|
68 |
+
---
|
69 |
|
70 |
+
*This model card was created with care by Ryan Witzman.*
|
71 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
+
Feel free to customize this template to better fit your model's personality and features!
|