commit

cnnlstm_test.sh

@@ -12,7 +12,8 @@ conda activate spring-2024-pyt
 export PYTHONPATH="/projectnb/ds598/admin/tgardos/sp2024_midterm:$PYTHONPATH"
 
 #python -m spacy download en_core_web_sm   # download spacy model
-python src/cnn_lstm/test.py
+python /projectnb/ds598/students/nikhitam/sp2024_midterm/src/demo_model/test.py
+
 
 ### The command below is used to submit the job to the cluster
 ### qsub -pe omp 4 -P ds598 -l gpus=1 cnnlstm_test.sh

cnnlstm_train.sh

@@ -12,7 +12,8 @@ conda activate spring-2024-pyt
 export PYTHONPATH="/projectnb/ds598/admin/tgardos/sp2024_midterm:$PYTHONPATH" # Set this!!!
 
 python -m spacy download en_core_web_sm   # download spacy model
-python src/cnn_lstm/train.py
+python /projectnb/ds598/students/nikhitam/sp2024_midterm/src/demo_model/train.py
+
 
 ### The command below is used to submit the job to the cluster
 ### qsub -pe omp 4 -P ds598 -l gpus=1 cnnlstm_train.sh

demo_test.sh

@@ -8,10 +8,12 @@ module load academic-ml/spring-2024
 
 conda activate spring-2024-pyt
 
+python -m spacy download en_core_web_sm
+
 # Change this path to point to your project directory
-export PYTHONPATH="/projectnb/ds598/admin/tgardos/sp2024_midterm:$PYTHONPATH" # Set this!!!
+export PYTHONPATH="/projectnb/ds598/students/nikhitam/sp2024_midterm:$PYTHONPATH" # Set this!!!
 
 python src/demo_model/test.py
 
 ### The command below is used to submit the job to the cluster
-### qsub -pe omp 4 -P ds598 -l gpus=1 git_test.sh
+qsub -pe omp 4 -P ds598 -l gpus=4 demo_test.sh

demo_train.sh

@@ -7,11 +7,17 @@ module load miniconda
 module load academic-ml/spring-2024
 
 conda activate spring-2024-pyt
+python -m spacy download en_core_web_sm
 
 # Change this path to point to your project directory
-export PYTHONPATH="/projectnb/ds598/admin/tgardos/sp2024_midterm:$PYTHONPATH"
+export PYTHONPATH="/projectnb/ds598/students/nikhitam/sp2024_midterm:$PYTHONPATH"
 
 python src/demo_model/train.py
 
+
+
 ### The command below is used to submit the job to the cluster
-### qsub -pe omp 4 -P ds598 -l gpus=1 demo_train.sh
+##qsub -pe omp 4 -P ds598 -l gpus=2 demo_train.sh
+
+
+

misc/models--microsoft--git-base/blobs/25680694d145c7902098f2bcdd81c23d4fc8e598

@@ -0,0 +1,106 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "git_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vocab_size": 30522
+}