initial commit: model files

README.md

@@ -0,0 +1,18 @@
+---
+tags:
+- conversational
+- tagalog
+- filipino
+
+language:
+- tl 
+
+inference: false
+---
+
+# Tagalog DialoGPT
+
+This is an extension of the base Tagalog DialoGPT model (https://huggingface.co/gabtan99/dialogpt-medium-tagalog). 
+
+This model is trained on 52K original conversations and 52K synthetic conversations, where 10% of tokens in each utterance in the synthetic conversation are machine-generated tokens. 
+

config.json

@@ -0,0 +1,30 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "vocab_size": 50257
+}

eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(3.8593)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52dca599f04a52017bf9cb434e0a5e0574d0bc4dac9b06b424425a3f6d8083c3
+size 1444581337

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7230da7394fe2930dbfbbefb8e0af4babc0e5080640e01edade4b45d998dbe2
+size 1327