mjbuehler commited on
Commit
a871cf9
·
verified ·
1 Parent(s): 0352a4e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -195
README.md CHANGED
@@ -7,7 +7,7 @@ tags: []
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
- ```
11
  import torch
12
  from xlora.xlora_utils import load_model
13
 
@@ -21,7 +21,7 @@ model,tokenizer=load_model(model_name = XLoRa_model_name,
21
  eos_token_id= tokenizer('<end_of_turn>', add_special_tokens=False, ) ['input_ids'][0]
22
  ```
23
 
24
- ```
25
  def generate_XLoRA_Gemma (system_prompt='You a helpful assistant. You are familiar with materials science. ',
26
  prompt='What is spider silk in the context of bioinspired materials?',
27
  repetition_penalty=1.,num_beams=1,num_return_sequences=1,
@@ -58,201 +58,10 @@ def generate_XLoRA_Gemma (system_prompt='You a helpful assistant. You are famili
58
 
59
  ```
60
  Then, use as follows:
61
- ```
62
  from IPython.display import display, Markdown
63
  q='''What is graphene?'''
64
  res=generate_XLoRA_Gemma( system_prompt='You design materials.', prompt=q, max_new_tokens=1024, temperature=0.3, eos_token=eos_token_id)
65
  display (Markdown(res))
66
- ```
67
- ## Model Details
68
-
69
- ### Model Description
70
-
71
- <!-- Provide a longer summary of what this model is. -->
72
-
73
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
74
-
75
- - **Developed by:** [More Information Needed]
76
- - **Funded by [optional]:** [More Information Needed]
77
- - **Shared by [optional]:** [More Information Needed]
78
- - **Model type:** [More Information Needed]
79
- - **Language(s) (NLP):** [More Information Needed]
80
- - **License:** [More Information Needed]
81
- - **Finetuned from model [optional]:** [More Information Needed]
82
-
83
- ### Model Sources [optional]
84
-
85
- <!-- Provide the basic links for the model. -->
86
-
87
- - **Repository:** [More Information Needed]
88
- - **Paper [optional]:** [More Information Needed]
89
- - **Demo [optional]:** [More Information Needed]
90
-
91
- ## Uses
92
-
93
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
94
-
95
-
96
-
97
- ### Direct Use
98
-
99
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
100
-
101
- [More Information Needed]
102
-
103
- ### Downstream Use [optional]
104
-
105
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
106
-
107
- [More Information Needed]
108
-
109
- ### Out-of-Scope Use
110
-
111
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
112
-
113
- [More Information Needed]
114
-
115
- ## Bias, Risks, and Limitations
116
-
117
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
118
-
119
- [More Information Needed]
120
-
121
- ### Recommendations
122
-
123
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
124
-
125
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
126
-
127
- ## How to Get Started with the Model
128
-
129
- Use the code below to get started with the model.
130
-
131
- [More Information Needed]
132
-
133
- ## Training Details
134
-
135
- ### Training Data
136
-
137
- <!-- 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. -->
138
-
139
- [More Information Needed]
140
-
141
- ### Training Procedure
142
-
143
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
144
-
145
- #### Preprocessing [optional]
146
-
147
- [More Information Needed]
148
-
149
-
150
- #### Training Hyperparameters
151
-
152
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
153
-
154
- #### Speeds, Sizes, Times [optional]
155
-
156
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
157
-
158
- [More Information Needed]
159
-
160
- ## Evaluation
161
-
162
- <!-- This section describes the evaluation protocols and provides the results. -->
163
-
164
- ### Testing Data, Factors & Metrics
165
-
166
- #### Testing Data
167
-
168
- <!-- This should link to a Dataset Card if possible. -->
169
-
170
- [More Information Needed]
171
-
172
- #### Factors
173
-
174
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
175
-
176
- [More Information Needed]
177
-
178
- #### Metrics
179
-
180
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
181
-
182
- [More Information Needed]
183
-
184
- ### Results
185
-
186
- [More Information Needed]
187
-
188
- #### Summary
189
-
190
-
191
-
192
- ## Model Examination [optional]
193
-
194
- <!-- Relevant interpretability work for the model goes here -->
195
-
196
- [More Information Needed]
197
-
198
- ## Environmental Impact
199
-
200
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
201
-
202
- 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).
203
-
204
- - **Hardware Type:** [More Information Needed]
205
- - **Hours used:** [More Information Needed]
206
- - **Cloud Provider:** [More Information Needed]
207
- - **Compute Region:** [More Information Needed]
208
- - **Carbon Emitted:** [More Information Needed]
209
-
210
- ## Technical Specifications [optional]
211
-
212
- ### Model Architecture and Objective
213
-
214
- [More Information Needed]
215
-
216
- ### Compute Infrastructure
217
-
218
- [More Information Needed]
219
-
220
- #### Hardware
221
-
222
- [More Information Needed]
223
-
224
- #### Software
225
-
226
- [More Information Needed]
227
-
228
- ## Citation [optional]
229
-
230
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
231
-
232
- **BibTeX:**
233
-
234
- [More Information Needed]
235
-
236
- **APA:**
237
-
238
- [More Information Needed]
239
-
240
- ## Glossary [optional]
241
-
242
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
243
-
244
- [More Information Needed]
245
-
246
- ## More Information [optional]
247
-
248
- [More Information Needed]
249
-
250
- ## Model Card Authors [optional]
251
-
252
- [More Information Needed]
253
-
254
- ## Model Card Contact
255
-
256
- [More Information Needed]
257
-
258
 
 
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
+ ```python
11
  import torch
12
  from xlora.xlora_utils import load_model
13
 
 
21
  eos_token_id= tokenizer('<end_of_turn>', add_special_tokens=False, ) ['input_ids'][0]
22
  ```
23
 
24
+ ```python
25
  def generate_XLoRA_Gemma (system_prompt='You a helpful assistant. You are familiar with materials science. ',
26
  prompt='What is spider silk in the context of bioinspired materials?',
27
  repetition_penalty=1.,num_beams=1,num_return_sequences=1,
 
58
 
59
  ```
60
  Then, use as follows:
61
+ ```python
62
  from IPython.display import display, Markdown
63
  q='''What is graphene?'''
64
  res=generate_XLoRA_Gemma( system_prompt='You design materials.', prompt=q, max_new_tokens=1024, temperature=0.3, eos_token=eos_token_id)
65
  display (Markdown(res))
66
+ ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67