spuun commited on
Commit
e8af8b0
1 Parent(s): 5290d00

Add model.

Browse files
README.md CHANGED
@@ -1,3 +1,27 @@
1
  ---
 
 
 
 
 
 
 
 
 
 
2
  license: cc-by-nc-sa-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - conversational
6
+ co2_eq_emissions:
7
+ emissions: "840"
8
+ source: "mlco2.github.io"
9
+ training_type: "fine-tuning"
10
+ geographical_location: "West Java, Indonesia"
11
+ hardware_used: "1 Tesla P100"
12
  license: cc-by-nc-sa-4.0
13
+ widget:
14
+ - text: "Hey kekbot! What's up?"
15
+ example_title: "Asking what's up"
16
+ - text: "Hey kekbot! How r u?"
17
+ example_title: "Asking how he is"
18
  ---
19
+ > THIS MODEL IS IN PUBLIC BETA, PLEASE DO NOT EXPECT ANY FORM OF STABILITY IN ITS CURRENT STATE.
20
+ # Art Union server chatbot
21
+
22
+ Based on a DialoGPT-medium (`kekbot-beta-3-medium`) model, fine-tuned to a select subset (65k<= messages) of Art Union's general-chat channel chat history.
23
+
24
+ ### Current issues
25
+ (Which hopefully will be fixed in future iterations) Include, but not limited to:
26
+ - Limited turns, after ~20 turns output may break for no apparent reason.
27
+ - Inconsistent variance, acts like an overfitted model from time to time for no reason whatsoever.
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "spuun/kekbot-beta-3-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "conversational": {
31
+ "max_length": 1000
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.19.1",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
eval_results.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ perplexity = tensor(1.1343)
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf5d2070be9a62cc9f2cb6ad6e87dcf89f5541492cfa1675e0310ccdc10b44a
3
+ size 1444566873
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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": "spuun/kekbot-beta-3-medium", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccc3176b254180593d030e48bc74d3a71ef260aecdacefa22454a80de229f4b
3
+ size 1327
vocab.json ADDED
The diff for this file is too large to render. See raw diff