Upload TFBlenderbotForConditionalGeneration

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model: facebook/blenderbot-400M-distill
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Blenderbot_ChatBot
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# Blenderbot_ChatBot
+
+This model is a fine-tuned version of [facebook/blenderbot-400M-distill](https://huggingface.co/facebook/blenderbot-400M-distill) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 3.4332
+- Epoch: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 6e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 6e-05, 'decay_steps': 2749, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Epoch |
+|:----------:|:-----:|
+| 3.4332     | 0     |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "facebook/blenderbot-400M-distill",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "BlenderbotForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1280,
+  "decoder_attention_heads": 32,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 32,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "extra_layer_norm": false,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "prelayernorm",
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "max_position_embeddings": 128,
+  "min_length": 20,
+  "model_type": "blenderbot",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 10,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "transformers_version": "4.33.2",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 8008
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "min_length": 20,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 10,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.2"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0bbe036f1b6d1466f21c850f46d871c6c367a870fc3e7ac1e88fec6b8676479
+size 1459650480