trained model on artEmis-V2

SELVM_on_artEmis-V2/ckpt_stats_best-res.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995e5481d55d5ee288d01fffdbbef507e72f6540b97a961248d0c1990e395d02
+size 802238115

SELVM_on_artEmis-V2/nle_gpt2_tokenizer_0/added_tokens.json

@@ -0,0 +1 @@
+{"<pad>": 50257, "<prefix>": 50258, "<emotion>": 50259, "<explanation>": 50260}

SELVM_on_artEmis-V2/nle_gpt2_tokenizer_0/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>", "additional_special_tokens": ["<prefix>", "<emotion>", "<explanation>"]}

SELVM_on_artEmis-V2/nle_gpt2_tokenizer_0/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/home/tanmoy/.cache/huggingface/transformers/accb287b5a5396b2597382916b6cc939fdab1366e89475a92338d3971b3d02b7.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "/zhangjing/datas/nlxgpt_pretrainedmodels/pretrain_tokenizer_0_for_artEmis", "tokenizer_class": "GPT2Tokenizer"}

SELVM_on_artEmis-V2/nle_model_best-res/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/zhangjing/datas/nlxgpt_pretrainedmodels/pretrain_model",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "add_cross_attention": true,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "encoder_dim": 768,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "img_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "len_prefix": 0,
+  "max_seq_len": 70,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "num_emotion": 9,
+  "prefix_size": 768,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_VAD_loss": true,
+  "use_cache": true,
+  "use_cl_loss": true,
+  "use_distribution_embedding": null,
+  "use_distribution_loss": null,
+  "use_emotion_embedding": null,
+  "use_exp_loss": true,
+  "use_position_loss": false,
+  "vocab_size": 50261
+}

SELVM_on_artEmis-V2/nle_model_best-res/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09540ee5e46e94398d6691ce1012765f8ec3b48368fccdab9d630ffc6faec093
+size 413585461