Text Generation
GGUF
English
Inference Endpoints
Jan commited on
Commit
1750c78
1 Parent(s): 8495b94

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ datasets:
4
+ - Intel/orca_dpo_pairs
5
+ - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
6
+ language:
7
+ - en
8
+ pipeline_tag: text-generation
9
+ ---
10
+
11
+
12
+
13
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63a259d0f30c46422789d38d/tmdM1fjNAmzV125zWd3_J.png)
14
+
15
+ # Go Bruins V2 - A Fine-tuned Language Model
16
+
17
+ ## Updates
18
+
19
+ ## Overview
20
+
21
+ **Go Bruins-V2** is a language model fine-tuned on the rwitz/go-bruins architecture. It's designed to push the boundaries of NLP applications, offering unparalleled performance in generating human-like text.
22
+
23
+ ## Model Details
24
+
25
+ - **Developer:** Ryan Witzman
26
+ - **Base Model:** [rwitz/go-bruins](https://huggingface.co/rwitz/go-bruins)
27
+ - **Fine-tuning Method:** Direct Preference Optimization (DPO)
28
+ - **Training Steps:** 642
29
+ - **Language:** English
30
+ - **License:** MIT
31
+
32
+ ## Capabilities
33
+
34
+ Go Bruins excels in a variety of NLP tasks, including but not limited to:
35
+ - Text generation
36
+ - Language understanding
37
+ - Sentiment analysis
38
+
39
+ ## Usage
40
+
41
+ **Warning:** This model may output NSFW or illegal content. Use with caution and at your own risk.
42
+
43
+ ### For Direct Use:
44
+
45
+ ```python
46
+ from transformers import pipeline
47
+
48
+ model_name = "rwitz/go-bruins-v2"
49
+ inference_pipeline = pipeline('text-generation', model=model_name)
50
+
51
+ input_text = "Your input text goes here"
52
+ output = inference_pipeline(input_text)
53
+
54
+ print(output)
55
+ ```
56
+
57
+
58
+ ### Not Recommended For:
59
+
60
+ - Illegal activities
61
+ - Harassment
62
+ - Professional advice or crisis situations
63
+
64
+ ## Training and Evaluation
65
+
66
+ Trained on a dataset from [athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW](https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW), Go Bruins V2 has shown promising improvements over its predecessor, Go Bruins.
67
+
68
+ # Evaluations
69
+
70
+ | Metric | Average | Arc Challenge | Hella Swag | MMLU | Truthful Q&A | Winogrande | GSM8k |
71
+ |---------------|---------|---------------|------------|------|--------------|------------|-------|
72
+ | **Score** | 72.07 | 69.8 | 87.05| 64.75 | 59.7 | 81.45 | 69.67 |
73
+
74
+ Note: The original MMLU evaluation has been corrected to include 5-shot data rather than 1-shot data.
75
+ ## Contact
76
+
77
+ For any inquiries or feedback, reach out to Ryan Witzman on Discord: `rwitz_`.
78
+
79
+ ---
80
+ ## Citations
81
+ ```
82
+ @misc{unacybertron7b,
83
+ title={Cybertron: Uniform Neural Alignment},
84
+ author={Xavier Murias},
85
+ year={2023},
86
+ publisher = {HuggingFace},
87
+ journal = {HuggingFace repository},
88
+ howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16}},
89
+ }
90
+ ```
91
+
92
+ *This model card was created with care by Ryan Witzman.*
93
+ rewrite this model card for new version called go-bruins-v2 that is finetuned on dpo on the original go-bruins model on athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW