Skip to content

Commit 0cf43f4

Browse files
EliSchwartzEliSchwartz
committed
minor corrections
1 parent 401e3fd commit 0cf43f4

File tree

1 file changed

+23
-24
lines changed

1 file changed

+23
-24
lines changed

‎notebooks/en/fine_tuning_granite_vision_sft_trl.ipynb‎

Lines changed: 23 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@
1919
"id": "JATmSI8mcyW2"
2020
},
2121
"source": [
22-
"In this recipe, we’ll demonstrate how to fine-tune [IBM's Granite Vision 3.1 2B Model](https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview).\n",
22+
"This recipe will enable you to fine-tune [IBM's Granite Vision 3.1 2B Model](https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview).\n",
2323
"It is a lightweight yet capable model trained by fine-tuning a [Granite language model](https://huggingface.co/ibm-granite/granite-3.1-2b-instruct) with both image and text modalities.\n",
2424
"We will be using the Hugging Face ecosystem, leveraging the powerful [Transformer Reinforcement Learning library (TRL)](https://huggingface.co/docs/trl/index). This step-by-step guide will enable you to Granite Vision for your specific tasks, even on consumer GPUs.\n",
2525
"\n",
@@ -44,7 +44,7 @@
4444
},
4545
{
4646
"cell_type": "code",
47-
"execution_count": 1,
47+
"execution_count": null,
4848
"metadata": {
4949
"id": "GCMhPmFdIGSb"
5050
},
@@ -57,7 +57,7 @@
5757
},
5858
{
5959
"cell_type": "code",
60-
"execution_count": 2,
60+
"execution_count": null,
6161
"metadata": {
6262
"colab": {
6363
"base_uri": "https://localhost:8080/"
@@ -297,15 +297,14 @@
297297
"source": [
298298
"## 3. Load Model and Check Performance! 🤔\n",
299299
"\n",
300-
"Now that we’ve loaded the dataset, it’s time to load the [IBM's Granite Vision Model](https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview), a 3\n",
301-
"2B parameter Vision Language Model (VLM) built on that offers state-of-the-art (SOTA) performance while being efficient in terms of memory usage.\n",
300+
"Now that we’ve loaded the dataset, it’s time to load the [IBM's Granite Vision Model](https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview), a 2B parameter Vision Language Model (VLM) built on that offers state-of-the-art (SOTA) performance while being efficient in terms of memory usage.\n",
302301
"\n",
303302
"For a broader comparison of state-of-the-art VLMs, explore the [WildVision Arena](https://huggingface.co/spaces/WildVision/vision-arena) and the [OpenVLM Leaderboard](https://huggingface.co/spaces/opencompass/open_vlm_leaderboard), where you can find the best-performing models across various benchmarks.\n"
304303
]
305304
},
306305
{
307306
"cell_type": "code",
308-
"execution_count": 9,
307+
"execution_count": null,
309308
"metadata": {
310309
"id": "PCJhM6tCw4lq"
311310
},
@@ -328,7 +327,7 @@
328327
},
329328
{
330329
"cell_type": "code",
331-
"execution_count": 10,
330+
"execution_count": null,
332331
"metadata": {
333332
"collapsed": true,
334333
"id": "awtjIq86JfFF",
@@ -384,7 +383,7 @@
384383
},
385384
{
386385
"cell_type": "code",
387-
"execution_count": 11,
386+
"execution_count": null,
388387
"metadata": {
389388
"id": "i-eIIdL9lqJJ"
390389
},
@@ -424,7 +423,7 @@
424423
},
425424
{
426425
"cell_type": "code",
427-
"execution_count": 12,
426+
"execution_count": null,
428427
"metadata": {
429428
"id": "QavnLzjJUbxf"
430429
},
@@ -456,7 +455,7 @@
456455
},
457456
{
458457
"cell_type": "code",
459-
"execution_count": 13,
458+
"execution_count": null,
460459
"metadata": {
461460
"id": "_MoRTjFcE8qD"
462461
},
@@ -503,7 +502,7 @@
503502
},
504503
{
505504
"cell_type": "code",
506-
"execution_count": 14,
505+
"execution_count": null,
507506
"metadata": {
508507
"colab": {
509508
"base_uri": "https://localhost:8080/",
@@ -552,7 +551,7 @@
552551
},
553552
{
554553
"cell_type": "code",
555-
"execution_count": 15,
554+
"execution_count": null,
556555
"metadata": {
557556
"id": "dxkXZuUkvy8j"
558557
},
@@ -617,7 +616,7 @@
617616
},
618617
{
619618
"cell_type": "code",
620-
"execution_count": 16,
619+
"execution_count": null,
621620
"metadata": {
622621
"id": "zm_bJRrXsESg"
623622
},
@@ -680,7 +679,7 @@
680679
},
681680
{
682681
"cell_type": "code",
683-
"execution_count": 17,
682+
"execution_count": null,
684683
"metadata": {
685684
"id": "ITmkRHWCKYjf"
686685
},
@@ -724,7 +723,7 @@
724723
},
725724
{
726725
"cell_type": "code",
727-
"execution_count": 18,
726+
"execution_count": null,
728727
"metadata": {
729728
"id": "SbqX1pQUKaSM"
730729
},
@@ -779,7 +778,7 @@
779778
},
780779
{
781780
"cell_type": "code",
782-
"execution_count": 19,
781+
"execution_count": null,
783782
"metadata": {
784783
"id": "pAzDovzylQeZ"
785784
},
@@ -859,7 +858,7 @@
859858
},
860859
{
861860
"cell_type": "code",
862-
"execution_count": 21,
861+
"execution_count": null,
863862
"metadata": {
864863
"id": "p1rgMTBDLboO"
865864
},
@@ -940,7 +939,7 @@
940939
},
941940
{
942941
"cell_type": "code",
943-
"execution_count": 22,
942+
"execution_count": null,
944943
"metadata": {
945944
"id": "tE8usZw0lgrL"
946945
},
@@ -971,7 +970,7 @@
971970
},
972971
{
973972
"cell_type": "code",
974-
"execution_count": 23,
973+
"execution_count": null,
975974
"metadata": {
976975
"colab": {
977976
"base_uri": "https://localhost:8080/"
@@ -1004,7 +1003,7 @@
10041003
},
10051004
{
10061005
"cell_type": "code",
1007-
"execution_count": 24,
1006+
"execution_count": null,
10081007
"metadata": {
10091008
"id": "EFqTNUud2lA7"
10101009
},
@@ -1046,7 +1045,7 @@
10461045
},
10471046
{
10481047
"cell_type": "code",
1049-
"execution_count": 25,
1048+
"execution_count": null,
10501049
"metadata": {
10511050
"id": "mQi2xBXk4sHe"
10521051
},
@@ -1067,7 +1066,7 @@
10671066
},
10681067
{
10691068
"cell_type": "code",
1070-
"execution_count": 26,
1069+
"execution_count": null,
10711070
"metadata": {
10721071
"colab": {
10731072
"base_uri": "https://localhost:8080/"
@@ -1099,7 +1098,7 @@
10991098
},
11001099
{
11011100
"cell_type": "code",
1102-
"execution_count": 27,
1101+
"execution_count": null,
11031102
"metadata": {
11041103
"id": "ATuQ6ZS6eirO"
11051104
},
@@ -1122,7 +1121,7 @@
11221121
},
11231122
{
11241123
"cell_type": "code",
1125-
"execution_count": 28,
1124+
"execution_count": null,
11261125
"metadata": {
11271126
"colab": {
11281127
"base_uri": "https://localhost:8080/",

0 commit comments

Comments
 (0)