dr_domi/udlbook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update CM20315_Transformers.ipynb

Browse Source
This commit is contained in:
Pietro Monticone
2023-11-30 16:46:38 +01:00
parent 193e2329f2
commit fefef63df4
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CM20315/CM20315_Transformers.ipynb
View File

@@ -175,7 +175,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"source": [ "source": [
"# TODO Modify the code below by changeing the number of tokens generated and the initial sentence\n", "# TODO Modify the code below by changing the number of tokens generated and the initial sentence\n",
"# to get a feel for how well this works. Since I didn't reset the seed, it will give a different\n", "# to get a feel for how well this works. Since I didn't reset the seed, it will give a different\n",
"# answer every time that you run it.\n", "# answer every time that you run it.\n",
"\n", "\n",
@@ -253,7 +253,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"source": [ "source": [
"# TODO Modify the code below by changeing the number of tokens generated and the initial sentence\n", "# TODO Modify the code below by changing the number of tokens generated and the initial sentence\n",
"# to get a feel for how well this works. \n", "# to get a feel for how well this works. \n",
"\n", "\n",
"# TODO Experiment with changing this line:\n", "# TODO Experiment with changing this line:\n",
@@ -471,7 +471,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"source": [ "source": [
"# This routine reutnrs the k'th most likely next token.\n", "# This routine returns the k'th most likely next token.\n",
"# If k =0 then it returns the most likely token, if k=1 it returns the next most likely and so on\n", "# If k =0 then it returns the most likely token, if k=1 it returns the next most likely and so on\n",
"# We will need this for beam search\n", "# We will need this for beam search\n",
"def get_kth_most_likely_token(input_tokens, model, tokenizer, k):\n", "def get_kth_most_likely_token(input_tokens, model, tokenizer, k):\n",