ctrltokyo commited on
Commit
09f7ae5
·
verified ·
1 Parent(s): 9f53f7f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -6
README.md CHANGED
@@ -6,16 +6,167 @@ tags:
6
  - unsloth
7
  - gemma3
8
  license: apache-2.0
 
9
  language:
10
  - en
11
  ---
12
 
13
- # Uploaded finetuned model
14
 
15
- - **Developed by:** TableCheck
16
- - **License:** apache-2.0
17
- - **Finetuned from model :** unsloth/gemma-3-27b-it-unsloth-bnb-4bit
18
 
19
- This gemma3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
20
 
21
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  - unsloth
7
  - gemma3
8
  license: apache-2.0
9
+ library_name: peft
10
  language:
11
  - en
12
  ---
13
 
14
+ # Model Card for TableCheck's Fine-Tune of google/gemma-3-27b-it
15
 
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+ This fine-tuned model is designed for use with function calls to translate content between languages and extract tags from content.
18
+ It has been trained on public data.
19
 
 
20
 
21
+
22
+ ## Model Details
23
+
24
+ ### Model Description
25
+
26
+ <!-- Provide a longer summary of what this model is. -->
27
+
28
+
29
+
30
+ - **Developed by:** TableCheck AI
31
+ - **Funded by:** TableCheck
32
+ - **Shared by:** TableCheck
33
+ - **Model type:** LoRa Adaptor
34
+ - **Language(s) (NLP):** English / Japanese / Gemma 3 27B Supported Languages
35
+ - **License:** Copyright TableCheck
36
+ - **Finetuned from model:** google/gemma-3-27b-it
37
+
38
+ ### Model Sources [optional]
39
+
40
+ <!-- Provide the basic links for the model. -->
41
+ Trained from public data of venues.
42
+
43
+ ## How to Get Started with the Model
44
+
45
+ Use the code below to get started with the model.
46
+ TBD
47
+
48
+ ## Training Details
49
+
50
+ ### Training Data
51
+
52
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
53
+ TBD
54
+
55
+ [More Information Needed]
56
+
57
+ ### Training Procedure
58
+
59
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
60
+ TBD
61
+
62
+
63
+ #### Training Hyperparameters
64
+
65
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
66
+
67
+ #### Speeds, Sizes, Times [optional]
68
+
69
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
70
+
71
+ [More Information Needed]
72
+
73
+ ## Evaluation
74
+
75
+ <!-- This section describes the evaluation protocols and provides the results. -->
76
+
77
+ ### Testing Data, Factors & Metrics
78
+
79
+ #### Testing Data
80
+
81
+ <!-- This should link to a Dataset Card if possible. -->
82
+
83
+ [More Information Needed]
84
+
85
+ #### Factors
86
+
87
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
88
+
89
+ [More Information Needed]
90
+
91
+ #### Metrics
92
+
93
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
94
+
95
+ [More Information Needed]
96
+
97
+ ### Results
98
+
99
+ [More Information Needed]
100
+
101
+ #### Summary
102
+
103
+
104
+
105
+ ## Model Examination [optional]
106
+
107
+ <!-- Relevant interpretability work for the model goes here -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Environmental Impact
112
+
113
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
114
+
115
+ 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).
116
+
117
+ - **Hardware Type:** [More Information Needed]
118
+ - **Hours used:** [More Information Needed]
119
+ - **Cloud Provider:** [More Information Needed]
120
+ - **Compute Region:** [More Information Needed]
121
+ - **Carbon Emitted:** [More Information Needed]
122
+
123
+ ## Technical Specifications [optional]
124
+
125
+ ### Model Architecture and Objective
126
+
127
+ [More Information Needed]
128
+
129
+ ### Compute Infrastructure
130
+
131
+ [More Information Needed]
132
+
133
+ #### Hardware
134
+
135
+ [More Information Needed]
136
+
137
+ #### Software
138
+
139
+ [More Information Needed]
140
+
141
+ ## Citation [optional]
142
+
143
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
144
+
145
+ **BibTeX:**
146
+
147
+ [More Information Needed]
148
+
149
+ **APA:**
150
+
151
+ [More Information Needed]
152
+
153
+ ## Glossary [optional]
154
+
155
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
156
+
157
+ [More Information Needed]
158
+
159
+ ## More Information [optional]
160
+
161
+ [More Information Needed]
162
+
163
+ ## Model Card Authors [optional]
164
+
165
+ [More Information Needed]
166
+
167
+ ## Model Card Contact
168
+
169
+ [More Information Needed]
170
+ ### Framework versions
171
+
172
+ - PEFT 0.15.0