rajabmondal commited on
Commit
608f806
·
verified ·
1 Parent(s): 13a1e36

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -67,6 +67,8 @@ The model is tailored for commercial use in Java programming tasks. It is partic
67
  3. Code generation and completion tasks in Java.
68
  4. FIM (code infilling) tasks specific to Java.
69
 
 
 
70
  # How to Use
71
 
72
  ## Sample inference code
@@ -114,7 +116,8 @@ inputs = tokenizer.encode("public class HelloWorld {\n public static void mai
114
  outputs = model.generate(inputs)
115
  print(tokenizer.decode(outputs[0]))
116
  ```
117
-
 
118
  # Attribution & Other Requirements
119
 
120
  The pretraining dataset for the model was curated to include only data with permissive licenses. Despite this, the model is capable of generating source code verbatim from the dataset. The licenses of such code may necessitate attribution and adherence to other specific conditions. To facilitate compliance, we provide a [search index](https://huggingface.co/spaces/bigcode/search) that enables users to trace the origins of generated code within the pretraining data, allowing for proper attribution and adherence to licensing requirements.
@@ -122,7 +125,9 @@ The pretraining dataset for the model was curated to include only data with perm
122
  # Limitations
123
 
124
  The NT-Java-1.1B model has been trained on publicly available datasets and is offered without any safety guarantees. As with all language models, its outputs are inherently unpredictable, and the generated code may not perform as expected. Additionally, the code may be inefficient or contain bugs and security vulnerabilities. Consequently, it is imperative for users and developers to undertake extensive safety testing and to implement robust filtering mechanisms tailored to their specific needs.
125
-
 
 
126
  # Training
127
 
128
  ## Model
@@ -145,6 +150,7 @@ The NT-Java-1.1B model has been trained on publicly available datasets and is of
145
 
146
  # License
147
  The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).
 
148
  # Citation
149
  ```
150
  @article{li2023starcoder,
 
67
  3. Code generation and completion tasks in Java.
68
  4. FIM (code infilling) tasks specific to Java.
69
 
70
+ <br>
71
+
72
  # How to Use
73
 
74
  ## Sample inference code
 
116
  outputs = model.generate(inputs)
117
  print(tokenizer.decode(outputs[0]))
118
  ```
119
+ <br>
120
+
121
  # Attribution & Other Requirements
122
 
123
  The pretraining dataset for the model was curated to include only data with permissive licenses. Despite this, the model is capable of generating source code verbatim from the dataset. The licenses of such code may necessitate attribution and adherence to other specific conditions. To facilitate compliance, we provide a [search index](https://huggingface.co/spaces/bigcode/search) that enables users to trace the origins of generated code within the pretraining data, allowing for proper attribution and adherence to licensing requirements.
 
125
  # Limitations
126
 
127
  The NT-Java-1.1B model has been trained on publicly available datasets and is offered without any safety guarantees. As with all language models, its outputs are inherently unpredictable, and the generated code may not perform as expected. Additionally, the code may be inefficient or contain bugs and security vulnerabilities. Consequently, it is imperative for users and developers to undertake extensive safety testing and to implement robust filtering mechanisms tailored to their specific needs.
128
+
129
+ <br>
130
+
131
  # Training
132
 
133
  ## Model
 
150
 
151
  # License
152
  The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).
153
+
154
  # Citation
155
  ```
156
  @article{li2023starcoder,