Add model

README.md

@@ -1,3 +1,27 @@
 ---
-license: cc-by-sa-4.0
+language:
+- en
+tags:
+- conversational
+co2_eq_emissions:
+      emissions: "940"
+      source: "mlco2.github.io"
+      training_type: "fine-tuning"
+      geographical_location: "West Java, Indonesia"
+      hardware_used: "1 Tesla P100"
+license: cc-by-nc-sa-4.0
+widget:
+- text: "Hey kekbot! What's up?"
+  example_title: "Asking what's up"
+- text: "Hey kekbot! How r u?"
+  example_title: "Asking how he is"
 ---
+> THIS MODEL IS IN PUBLIC BETA, PLEASE DO NOT EXPECT ANY FORM OF STABILITY IN ITS CURRENT STATE.  
+# Art Union server chatbot
+
+Based on a DialoGPT-medium model, fine-tuned to a small subset (115k<= messages) of Art Union's general-chat channel.
+
+### Current issues  
+(Which hopefully will be fixed in future iterations) Include, but not limited to:
+- Limited turns, after ~11 turns output may break for no apparent reason.
+- Inconsistent variance, acts like an overfitted model from time to time for no reason whatsoever.

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "output/checkpoint-40000",
+  "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_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(1.2290)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0366a658ece9400201c40ffdd8b15d2e0efc27f5a27669de86f1182f43cb68
+size 1444566873

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}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"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, "name_or_path": "microsoft/DialoGPT-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7c4c43ad0f21a007d923f6426ba428c085b63d891a8235c5e97dccacc567d5
+size 1327