Dongwookss commited on
Commit
60bbd01
β€’
1 Parent(s): c1924f3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -61
README.md CHANGED
@@ -10,71 +10,19 @@ tags:
10
  - transformer
11
  ---
12
 
 
13
 
14
- Base Model : HuggingFaceH4/zephyr-7b-beta
15
- QLoRA μ΄μš©ν•˜μ—¬ νŠœλ‹ μ§„ν–‰ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
16
- 데이터셋은 ν’‹μ‚΄ 도메인 챗봇을 μœ„ν•΄ 직접 κ΅¬μΆ•ν•œ 데이터와 κΈ°μ‘΄ 타 λ°μ΄ν„°μ˜ 말투λ₯Ό μˆ˜μ •ν•˜μ—¬ ν•™μŠ΅ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
17
 
18
- #### Summary
19
 
 
20
 
 
 
 
 
 
 
21
 
22
- ## Model Examination [optional]
23
 
24
- <!-- Relevant interpretability work for the model goes here -->
25
 
26
- [More Information Needed]
27
-
28
- ## Environmental Impact
29
-
30
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
31
-
32
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
33
-
34
- - **Hardware Type:** [More Information Needed]
35
- - **Hours used:** [More Information Needed]
36
- - **Cloud Provider:** [More Information Needed]
37
- - **Compute Region:** [More Information Needed]
38
- - **Carbon Emitted:** [More Information Needed]
39
-
40
- ## Technical Specifications [optional]
41
-
42
- ### Model Architecture and Objective
43
-
44
- [More Information Needed]
45
-
46
- ### Compute Infrastructure
47
-
48
- [More Information Needed]
49
-
50
- #### Hardware
51
-
52
- [More Information Needed]
53
-
54
- #### Software
55
-
56
- [More Information Needed]
57
-
58
- ## Citation [optional]
59
-
60
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
61
-
62
- **BibTeX:**
63
-
64
- [More Information Needed]
65
-
66
- **APA:**
67
-
68
- [More Information Needed]
69
-
70
- ## Glossary [optional]
71
-
72
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
73
-
74
- [More Information Needed]
75
-
76
- ## More Information [optional]
77
-
78
- [More Information Needed]
79
-
80
- ## Model Card Authors [op
 
10
  - transformer
11
  ---
12
 
13
+ ### Base Model : HuggingFaceH4/zephyr-7b-beta
14
 
15
+ <img src="https://github.com/ddsntc1/Chatbot_FutFut/assets/38596856/cb1cd8b7-c556-46a8-ab8d-e093af713433.jpg" width="400" height="400">
 
 
16
 
 
17
 
18
+ #### Summary:
19
 
20
+ - **Unsloth** νŒ¨ν‚€μ§€λ₯Ό μ‚¬μš©ν•˜μ—¬ **LoRA** μ§„ν–‰ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
21
+ - **SFT Trainer**λ₯Ό 톡해 ν›ˆλ ¨μ„ 진행
22
+ - ν™œμš© 데이터
23
+ - [q_a_korean_futsal](https://huggingface.co/datasets/Dongwookss/q_a_korean_futsal)
24
+ - 말투 ν•™μŠ΅μ„ μœ„ν•΄ 'ν•΄μš”'체둜 λ³€ν™˜ν•˜κ³  λ‹΅λ³€ μ’…λ£Œμ‹œ 'μ–Όλ§ˆλ“ μ§€ λ¬Όμ–΄λ³΄μ„Έμš”~! ν’‹ν’‹~!'을 λ„£μ–΄ λͺ¨λΈ 컨셉을 μœ μ§€ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
25
+
26
 
 
27
 
 
28