s1s2q commited on
Commit
a438ee4
·
verified ·
1 Parent(s): 55df64d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -166
README.md CHANGED
@@ -18,19 +18,17 @@ language:
18
 
19
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
20
 
21
- - **Developed by:** [More Information Needed]
22
  - **Funded by [optional]:** [More Information Needed]
23
  - **Shared by [optional]:** [More Information Needed]
24
- - **Model type:** [More Information Needed]
25
- - **Language(s) (NLP):** [More Information Needed]
26
- - **License:** [More Information Needed]
27
- - **Finetuned from model [optional]:** [More Information Needed]
28
 
29
  ### Model Sources [optional]
30
 
31
  - **Demo [optional]:**
32
  ```
33
- from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
34
  import torch
35
 
36
  model_name = "eridai/eridaRE"
@@ -93,167 +91,23 @@ _ = model.generate(
93
  )
94
  ```
95
 
96
- ## Uses
 
 
 
97
 
98
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
99
 
100
- ### Direct Use
 
101
 
102
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
103
 
104
- [More Information Needed]
105
-
106
- ### Downstream Use [optional]
107
-
108
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
109
-
110
- [More Information Needed]
111
-
112
- ### Out-of-Scope Use
113
-
114
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
115
-
116
- [More Information Needed]
117
-
118
- ## Bias, Risks, and Limitations
119
-
120
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
121
-
122
- [More Information Needed]
123
-
124
- ### Recommendations
125
-
126
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
127
-
128
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
129
-
130
- ## How to Get Started with the Model
131
-
132
- Use the code below to get started with the model.
133
-
134
- [More Information Needed]
135
-
136
- ## Training Details
137
-
138
- ### Training Data
139
-
140
- <!-- 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. -->
141
-
142
- [More Information Needed]
143
-
144
- ### Training Procedure
145
-
146
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
147
-
148
- #### Preprocessing [optional]
149
-
150
- [More Information Needed]
151
-
152
-
153
- #### Training Hyperparameters
154
-
155
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
156
-
157
- #### Speeds, Sizes, Times [optional]
158
-
159
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
160
-
161
- [More Information Needed]
162
-
163
- ## Evaluation
164
-
165
- <!-- This section describes the evaluation protocols and provides the results. -->
166
-
167
- ### Testing Data, Factors & Metrics
168
-
169
- #### Testing Data
170
-
171
- <!-- This should link to a Dataset Card if possible. -->
172
-
173
- [More Information Needed]
174
-
175
- #### Factors
176
-
177
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
178
-
179
- [More Information Needed]
180
-
181
- #### Metrics
182
-
183
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
184
-
185
- [More Information Needed]
186
-
187
- ### Results
188
-
189
- [More Information Needed]
190
-
191
- #### Summary
192
-
193
-
194
-
195
- ## Model Examination [optional]
196
-
197
- <!-- Relevant interpretability work for the model goes here -->
198
-
199
- [More Information Needed]
200
-
201
- ## Environmental Impact
202
-
203
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
204
-
205
- 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).
206
-
207
- - **Hardware Type:** [More Information Needed]
208
- - **Hours used:** [More Information Needed]
209
- - **Cloud Provider:** [More Information Needed]
210
- - **Compute Region:** [More Information Needed]
211
- - **Carbon Emitted:** [More Information Needed]
212
-
213
- ## Technical Specifications [optional]
214
-
215
- ### Model Architecture and Objective
216
-
217
- [More Information Needed]
218
-
219
- ### Compute Infrastructure
220
-
221
- [More Information Needed]
222
-
223
- #### Hardware
224
-
225
- [More Information Needed]
226
-
227
- #### Software
228
-
229
- [More Information Needed]
230
-
231
- ## Citation [optional]
232
-
233
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
234
-
235
- **BibTeX:**
236
-
237
- [More Information Needed]
238
-
239
- **APA:**
240
-
241
- [More Information Needed]
242
-
243
- ## Glossary [optional]
244
-
245
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
246
-
247
- [More Information Needed]
248
-
249
- ## More Information [optional]
250
-
251
- [More Information Needed]
252
-
253
- ## Model Card Authors [optional]
254
-
255
- [More Information Needed]
256
-
257
- ## Model Card Contact
258
-
259
- [More Information Needed]
 
18
 
19
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
20
 
21
+ - **Developed by:** eridAI
22
  - **Funded by [optional]:** [More Information Needed]
23
  - **Shared by [optional]:** [More Information Needed]
24
+ - **Model type:** GPT-reasoner
25
+ - **Language(s) (NLP):** Russian
 
 
26
 
27
  ### Model Sources [optional]
28
 
29
  - **Demo [optional]:**
30
  ```
31
+ from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
32
  import torch
33
 
34
  model_name = "eridai/eridaRE"
 
91
  )
92
  ```
93
 
94
+ ### Output
95
+ >>> У Брайана есть несколько марок номиналом 3 цента и несколько марок номиналом 4 цента. Какое наименьшее количество марок он может объединить, чтобы их стоимость составляла 33 цента?
96
+ Сначала я определю, сколько марок по 3 и 4 цента я могу использовать, чтобы их общая стоимость составляла 33 цента. Я подумаю о том, как разбить 33 на суммы из 3 и 4. Возможно, я начну с наименьшего количества марок, например, с 0 марок по 4 цента и посмотреть, сколько марок по 3 цента мне понадобится. Если я использую 11 марок по 3 цента, это даст 33 цента, но тогда я использую 11 марок, что, возможно, не оптимально. Затем я попробую использовать 1 марку по 4 цента и посчитаю, сколько марок по 3 цента мне нужно: (33 - 4) = 29, и 29 делится на 3? 29/3 ≈ 9.666, что не целое число, поэтому это не подходит. Next, я попробую 2 марки по 4 цента: (33 - 8) = 25, 25/3 ≈ 8.333, также не целое. Потом 3 марки: (33 - 12) = 21, 21/3 = 7. Это целое! Значит, я могу использовать 3 марки по 4 цента и 7 марок по 3 цента, что даст 3 + 7 = 10 марок. Мне нужно проверить, есть ли способ с меньшим количеством марок. Допустим, я использую 4 марки по 4 цента: (33 - 16) = 17, 17/3 ≈ 5.666, не целое. 5 марок: (33 - 20) = 13, 13/3 ≈ 4.333, не целое. 6 марок: (33 - 24) = 9, 9/3 = 3. Значит, я могу использовать 6 марок по 4 цента и 3 марок по 3 цента, что даст 6 + 3 = 9 марок. Это лучше, чем 10. Проверю, есть ли еще лучший способ. 7 марок по 4 цента: (33 - 28) = 5, 5/3 ≈ 1.666, не целое. 8 марок: (33 - 32) = 1, 1/3 ≈ 0.333, не целое. 9 марок: (33 - 36) = -3, что не подходит. Значит, наименьшее количество марок равно 9.
97
+ </think>
98
 
99
+ Чтобы решить задачу,我们必须 найти наименьшее количество марок с nominalem 3 и 4 центов,能够让 их общая стоимость равняться 33 центам.
100
 
101
+ **Шаг 1:** Обозначим количество марок по 3 цента за \( x \), а по 4 цента за \( y \). Тогда общая стоимость марок может быть представлена уравнением:
102
+ \[ 3x + 4y = 33 \]
103
 
104
+ **Шаг 2:** Нам нужно найти наименьшее значение \( x + y \), при котором \( x \) и \( y \) — целые неотрицательные числа.
105
 
106
+ **Шаг 3:** Попробуем разные значения \( y \) и постараемся найти соответствующее \( x \), чтобы общая стоимость составляла 33 центов:
107
+ - Если \( y = 0 \), тогда \( 3x = 33 \) → \( x = 11 \). Всего марок: \( 11 + 0 = 11 \).
108
+ - Если \( y = 1 \), тогда \( 3x = 33 - 4 = 29 \) → \( x \) не целое.
109
+ - Если \( y = 2 \), тогда \( 3x = 33 - 8 = 25 \) → \( x \) не целое.
110
+ - Если \( y = 3 \), тогда \( 3
111
+ \[
112
+ \boxed{9}
113
+ \]<|end▁of▁sentence|>