MattStammers commited on
Commit
def8b5b
·
1 Parent(s): 70b91ba

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +47 -24
README.md CHANGED
@@ -24,6 +24,29 @@ get_started_code: "``` python \n # Use a pipeline as a high-level helper\n
24
  \ model = AutoModelForSequenceClassification.from_pretrained(\"MattStammers/test-trainer\"\
25
  )\n "
26
  training_data: 'see Glue dataset: https://huggingface.co/datasets/glue'
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  model-index:
28
  - name: test_trainer
29
  results:
@@ -132,18 +155,18 @@ see Glue dataset: https://huggingface.co/datasets/glue
132
 
133
  #### Preprocessing [optional]
134
 
135
- [More Information Needed]
136
 
137
 
138
  #### Training Hyperparameters
139
 
140
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
141
 
142
  #### Speeds, Sizes, Times [optional]
143
 
144
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
145
 
146
- [More Information Needed]
147
 
148
  ## Evaluation
149
 
@@ -155,33 +178,33 @@ see Glue dataset: https://huggingface.co/datasets/glue
155
 
156
  <!-- This should link to a Data Card if possible. -->
157
 
158
- [More Information Needed]
159
 
160
  #### Factors
161
 
162
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
163
 
164
- [More Information Needed]
165
 
166
  #### Metrics
167
 
168
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
169
 
170
- [More Information Needed]
171
 
172
  ### Results
173
 
174
- [More Information Needed]
175
 
176
  #### Summary
177
 
178
-
179
 
180
  ## Model Examination [optional]
181
 
182
  <!-- Relevant interpretability work for the model goes here -->
183
 
184
- [More Information Needed]
185
 
186
  ## Environmental Impact
187
 
@@ -189,29 +212,29 @@ see Glue dataset: https://huggingface.co/datasets/glue
189
 
190
  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).
191
 
192
- - **Hardware Type:** [More Information Needed]
193
- - **Hours used:** [More Information Needed]
194
- - **Cloud Provider:** [More Information Needed]
195
- - **Compute Region:** [More Information Needed]
196
- - **Carbon Emitted:** [More Information Needed]
197
 
198
  ## Technical Specifications [optional]
199
 
200
  ### Model Architecture and Objective
201
 
202
- [More Information Needed]
203
 
204
  ### Compute Infrastructure
205
 
206
- [More Information Needed]
207
 
208
  #### Hardware
209
 
210
- [More Information Needed]
211
 
212
  #### Software
213
 
214
- [More Information Needed]
215
 
216
  ## Citation [optional]
217
 
@@ -219,28 +242,28 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
219
 
220
  **BibTeX:**
221
 
222
- [More Information Needed]
223
 
224
  **APA:**
225
 
226
- [More Information Needed]
227
 
228
  ## Glossary [optional]
229
 
230
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
231
 
232
- [More Information Needed]
233
 
234
  ## More Information [optional]
235
 
236
- [More Information Needed]
237
 
238
  ## Model Card Authors [optional]
239
 
240
- [More Information Needed]
241
 
242
  ## Model Card Contact
243
 
244
- [More Information Needed]
245
 
246
 
 
24
  \ model = AutoModelForSequenceClassification.from_pretrained(\"MattStammers/test-trainer\"\
25
  )\n "
26
  training_data: 'see Glue dataset: https://huggingface.co/datasets/glue'
27
+ preprocessing: sentence pairs to analyse similarity
28
+ training_regime: user_defined
29
+ speeds_sizes_times: not_relevant
30
+ testing_data: 'MRCP. Link: https://huggingface.co/datasets/SetFit/mrpc'
31
+ testing_factors: unknown
32
+ testing_metrics: unknown
33
+ results: see evaluation results.
34
+ results_summary: results are not bad
35
+ model_examination: model should be interpreted with user discretion.
36
+ model_specs: bert fine-tuned
37
+ compute_infrastructure: requires less than 4GB of GPU to run quickly
38
+ hardware: T600
39
+ hours_used: '0.1'
40
+ cloud_provider: on-prem
41
+ cloud_region: europe
42
+ co2_emitted: very little
43
+ software: python, pytorch with transformers
44
+ citation_bibtex: nil_presently
45
+ citation_apa: not_relevant
46
+ glossary: nil presently
47
+ more_information: can be made available on request
48
+ model_card_authors: Matt Stammers
49
+ model_card_contact: Matt Stammers
50
  model-index:
51
  - name: test_trainer
52
  results:
 
155
 
156
  #### Preprocessing [optional]
157
 
158
+ sentence pairs to analyse similarity
159
 
160
 
161
  #### Training Hyperparameters
162
 
163
+ - **Training regime:** user_defined <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
164
 
165
  #### Speeds, Sizes, Times [optional]
166
 
167
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
168
 
169
+ not_relevant
170
 
171
  ## Evaluation
172
 
 
178
 
179
  <!-- This should link to a Data Card if possible. -->
180
 
181
+ MRCP. Link: https://huggingface.co/datasets/SetFit/mrpc
182
 
183
  #### Factors
184
 
185
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
186
 
187
+ unknown
188
 
189
  #### Metrics
190
 
191
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
192
 
193
+ unknown
194
 
195
  ### Results
196
 
197
+ see evaluation results.
198
 
199
  #### Summary
200
 
201
+ results are not bad
202
 
203
  ## Model Examination [optional]
204
 
205
  <!-- Relevant interpretability work for the model goes here -->
206
 
207
+ model should be interpreted with user discretion.
208
 
209
  ## Environmental Impact
210
 
 
212
 
213
  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).
214
 
215
+ - **Hardware Type:** T600
216
+ - **Hours used:** 0.1
217
+ - **Cloud Provider:** on-prem
218
+ - **Compute Region:** europe
219
+ - **Carbon Emitted:** very little
220
 
221
  ## Technical Specifications [optional]
222
 
223
  ### Model Architecture and Objective
224
 
225
+ bert fine-tuned
226
 
227
  ### Compute Infrastructure
228
 
229
+ requires less than 4GB of GPU to run quickly
230
 
231
  #### Hardware
232
 
233
+ T600
234
 
235
  #### Software
236
 
237
+ python, pytorch with transformers
238
 
239
  ## Citation [optional]
240
 
 
242
 
243
  **BibTeX:**
244
 
245
+ nil_presently
246
 
247
  **APA:**
248
 
249
+ not_relevant
250
 
251
  ## Glossary [optional]
252
 
253
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
254
 
255
+ nil presently
256
 
257
  ## More Information [optional]
258
 
259
+ can be made available on request
260
 
261
  ## Model Card Authors [optional]
262
 
263
+ Matt Stammers
264
 
265
  ## Model Card Contact
266
 
267
+ Matt Stammers
268
 
269