Upload model

config.json

@@ -6,18 +6,44 @@
     "_name_or_path": "hf-internal-testing/tiny-random-gpt2",
     "activation_function": "gelu_new",
     "add_cross_attention": true,
+    "architectures": null,
     "attention_probs_dropout_prob": 0.1,
     "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
     "bos_token_id": 98,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
     "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 98,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
     "gradient_checkpointing": false,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "initializer_range": 0.02,
     "intermediate_size": 37,
     "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "gpt2",
     "n_ctx": 512,
     "n_embd": 32,
@@ -25,44 +51,129 @@
     "n_inner": null,
     "n_layer": 5,
     "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
     "pad_token_id": 98,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
     "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
     "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
     "scale_attn_by_inverse_layer_idx": false,
     "scale_attn_weights": true,
+    "sep_token_id": null,
     "summary_activation": null,
     "summary_first_dropout": 0.1,
     "summary_proj_to_labels": true,
     "summary_type": "cls_index",
     "summary_use_proj": true,
-    "torch_dtype": "float32",
+    "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,
     "type_vocab_size": 16,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 1000
   },
   "encoder": {
     "_name_or_path": "hf-internal-testing/tiny-random-bert",
+    "add_cross_attention": false,
+    "architectures": null,
     "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "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,
     "gradient_checkpointing": false,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
     "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "initializer_range": 0.02,
     "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
     "max_position_embeddings": 512,
+    "min_length": 0,
     "model_type": "bert",
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
     "position_embedding_type": "absolute",
-    "torch_dtype": "float32",
+    "prefix": null,
+    "problem_type": null,
+    "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,
     "type_vocab_size": 16,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 1124
   },
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
   "torch_dtype": "float32",
-  "transformers_version": "4.53.3"
+  "transformers_version": "4.36.0"
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 98,
   "eos_token_id": 98,
   "pad_token_id": 98,
-  "transformers_version": "4.53.3"
+  "transformers_version": "4.36.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f671aecc66846277ef8c50b0b1c5c3ac6b5b3148bcd25f14350a776d0e19ac9a
+oid sha256:b45540d2f8dd35d5dd89dcfa425b7215d7b6115217965890a943c3c347c47d05
 size 906124