pbelcak commited on
Commit
06e495c
1 Parent(s): 2e95158

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -25,8 +25,13 @@ You can find the paper here: https://arxiv.org/abs/2311.10770, and the abstract
25
 
26
  This is the raw pretraining checkpoint. You can use this to fine-tune on a downstream task like GLUE as discussed in the paper. This model is provided only as sanity check for research purposes, it is untested and unfit for deployment.
27
 
28
- ### How to use
29
 
 
 
 
 
 
30
 
31
  ```python
32
  import cramming
@@ -40,6 +45,8 @@ encoded_input = tokenizer(text, return_tensors='pt')
40
  output = model(**encoded_input)
41
  ```
42
 
 
 
43
 
44
  ### Limitations and bias
45
 
 
25
 
26
  This is the raw pretraining checkpoint. You can use this to fine-tune on a downstream task like GLUE as discussed in the paper. This model is provided only as sanity check for research purposes, it is untested and unfit for deployment.
27
 
28
+ ### How to get started
29
 
30
+ 1. Create a new Python/conda environment, or simply use one that does not have any previous version of the original `cramming` project installed. If, by accident, you use the original cramming repository code instead of the one provided in the `/training` folder of this project, you will be warned by `transformers` that there are some extra weights (FFF weight) and that some weights are missing (the FF weights expected by the original `crammedBERT`).
31
+ 2. `cd ./training`
32
+ 3. `pip install .`
33
+ 4. Create `minimal_example.py`
34
+ 5. Paste the code below
35
 
36
  ```python
37
  import cramming
 
45
  output = model(**encoded_input)
46
  ```
47
 
48
+ 6. Run `python minimal_example.py`.
49
+
50
 
51
  ### Limitations and bias
52