penguintrainer commited on
Commit
bbff61e
·
verified ·
1 Parent(s): bf3f2c6
Files changed (1) hide show
  1. README.md +48 -26
README.md CHANGED
@@ -32,10 +32,13 @@ Used ichikara-instruction-003-001-1 for fineturning.
32
  [ichikara-instruction: 日本語instructionモデル評価データセット](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF-%E5%85%AC%E9%96%8B/)
33
  © 2023 Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura (CC BY-SA 4.0 )
34
 
 
35
  ### Model Description
 
36
 
37
  <!-- Provide a longer summary of what this model is. -->
38
 
 
39
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
40
 
41
  - **Developed by:** [More Information Needed]
@@ -48,12 +51,13 @@ This is the model card of a 🤗 transformers model that has been pushed on the
48
 
49
  ### Model Sources [optional]
50
 
 
51
  <!-- Provide the basic links for the model. -->
52
-
53
  - **Repository:** [More Information Needed]
54
  - **Paper [optional]:** [More Information Needed]
55
  - **Demo [optional]:** [More Information Needed]
56
-
57
  ## Uses
58
 
59
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
@@ -109,35 +113,44 @@ with torch.no_grad():
109
  print(tokenizer.decode(output))
110
 
111
  ```
 
112
 
113
  ### Direct Use
114
 
 
115
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
116
 
 
 
117
  [More Information Needed]
118
 
119
  ### Downstream Use [optional]
120
 
 
121
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
122
 
 
123
  [More Information Needed]
124
 
125
  ### Out-of-Scope Use
126
 
 
127
  <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
128
 
 
129
  [More Information Needed]
130
 
131
  ## Bias, Risks, and Limitations
 
132
 
133
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
134
-
135
  [More Information Needed]
136
 
137
  ### Recommendations
138
-
139
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
140
-
141
  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
142
 
143
  ## How to Get Started with the Model
@@ -149,15 +162,16 @@ Use the code below to get started with the model.
149
  ## Training Details
150
 
151
  ### Training Data
152
-
153
  <!-- 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. -->
154
 
 
155
  [More Information Needed]
156
 
157
  ### Training Procedure
158
-
159
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
160
-
161
  #### Preprocessing [optional]
162
 
163
  [More Information Needed]
@@ -165,36 +179,42 @@ Use the code below to get started with the model.
165
 
166
  #### Training Hyperparameters
167
 
168
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
169
 
 
 
 
 
 
170
  #### Speeds, Sizes, Times [optional]
171
 
 
172
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
173
 
 
174
  [More Information Needed]
175
 
176
  ## Evaluation
177
-
178
  <!-- This section describes the evaluation protocols and provides the results. -->
179
-
180
  ### Testing Data, Factors & Metrics
181
 
182
  #### Testing Data
183
-
184
  <!-- This should link to a Dataset Card if possible. -->
185
-
186
  [More Information Needed]
187
 
188
  #### Factors
189
-
190
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
191
-
192
  [More Information Needed]
193
 
194
  #### Metrics
195
-
196
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
197
-
198
  [More Information Needed]
199
 
200
  ### Results
@@ -206,15 +226,15 @@ Use the code below to get started with the model.
206
 
207
 
208
  ## Model Examination [optional]
209
-
210
  <!-- Relevant interpretability work for the model goes here -->
211
-
212
  [More Information Needed]
213
 
214
  ## Environmental Impact
215
-
216
  <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
217
-
218
  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).
219
 
220
  - **Hardware Type:** [More Information Needed]
@@ -242,9 +262,9 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
242
  [More Information Needed]
243
 
244
  ## Citation [optional]
245
-
246
  <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
247
-
248
  **BibTeX:**
249
 
250
  [More Information Needed]
@@ -254,9 +274,9 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
254
  [More Information Needed]
255
 
256
  ## Glossary [optional]
257
-
258
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
259
-
260
  [More Information Needed]
261
 
262
  ## More Information [optional]
@@ -269,4 +289,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
269
 
270
  ## Model Card Contact
271
 
272
- [More Information Needed]
 
 
 
32
  [ichikara-instruction: 日本語instructionモデル評価データセット](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF-%E5%85%AC%E9%96%8B/)
33
  © 2023 Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura (CC BY-SA 4.0 )
34
 
35
+ <!--
36
  ### Model Description
37
+ -->
38
 
39
  <!-- Provide a longer summary of what this model is. -->
40
 
41
+ <!--
42
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
43
 
44
  - **Developed by:** [More Information Needed]
 
51
 
52
  ### Model Sources [optional]
53
 
54
+ -->
55
  <!-- Provide the basic links for the model. -->
56
+ <!--
57
  - **Repository:** [More Information Needed]
58
  - **Paper [optional]:** [More Information Needed]
59
  - **Demo [optional]:** [More Information Needed]
60
+ -->
61
  ## Uses
62
 
63
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
113
  print(tokenizer.decode(output))
114
 
115
  ```
116
+ <!--
117
 
118
  ### Direct Use
119
 
120
+ -->
121
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
122
 
123
+ <!--
124
+
125
  [More Information Needed]
126
 
127
  ### Downstream Use [optional]
128
 
129
+ -->
130
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
131
 
132
+ <!--
133
  [More Information Needed]
134
 
135
  ### Out-of-Scope Use
136
 
137
+ -->
138
  <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
139
 
140
+ <!--
141
  [More Information Needed]
142
 
143
  ## Bias, Risks, and Limitations
144
+ -->
145
 
146
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
147
+ <!--
148
  [More Information Needed]
149
 
150
  ### Recommendations
151
+ -->
152
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
153
+ <!--
154
  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
155
 
156
  ## How to Get Started with the Model
 
162
  ## Training Details
163
 
164
  ### Training Data
165
+ -->
166
  <!-- 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. -->
167
 
168
+ <!--
169
  [More Information Needed]
170
 
171
  ### Training Procedure
172
+ -->
173
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
174
+ <!--
175
  #### Preprocessing [optional]
176
 
177
  [More Information Needed]
 
179
 
180
  #### Training Hyperparameters
181
 
 
182
 
183
+ - **Training regime:** [More Information Needed]
184
+ -->
185
+ <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
186
+
187
+ <!--
188
  #### Speeds, Sizes, Times [optional]
189
 
190
+ -->
191
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
192
 
193
+ <!--
194
  [More Information Needed]
195
 
196
  ## Evaluation
197
+ -->
198
  <!-- This section describes the evaluation protocols and provides the results. -->
199
+ <!--
200
  ### Testing Data, Factors & Metrics
201
 
202
  #### Testing Data
203
+ -->
204
  <!-- This should link to a Dataset Card if possible. -->
205
+ <!--
206
  [More Information Needed]
207
 
208
  #### Factors
209
+ -->
210
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
211
+ <!--
212
  [More Information Needed]
213
 
214
  #### Metrics
215
+ -->
216
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
217
+ <!--
218
  [More Information Needed]
219
 
220
  ### Results
 
226
 
227
 
228
  ## Model Examination [optional]
229
+ -->
230
  <!-- Relevant interpretability work for the model goes here -->
231
+ <!--
232
  [More Information Needed]
233
 
234
  ## Environmental Impact
235
+ -->
236
  <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
237
+ <!--
238
  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).
239
 
240
  - **Hardware Type:** [More Information Needed]
 
262
  [More Information Needed]
263
 
264
  ## Citation [optional]
265
+ -->
266
  <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
267
+ <!--
268
  **BibTeX:**
269
 
270
  [More Information Needed]
 
274
  [More Information Needed]
275
 
276
  ## Glossary [optional]
277
+ -->
278
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
279
+ <!--
280
  [More Information Needed]
281
 
282
  ## More Information [optional]
 
289
 
290
  ## Model Card Contact
291
 
292
+ [More Information Needed]
293
+
294
+ -->