TearGosling commited on
Commit
0afbe0c
1 Parent(s): 4c489e1

Upload main model (test)

Browse files

This may or may not work, due to not purging ColossalAI details from model yet. If this doesn't work, we'll update the file

README.md CHANGED
@@ -1,3 +1,7 @@
1
- ---
2
- license: other
3
- ---
 
 
 
 
1
+ # pygmalion-350m
2
+
3
+ # Model description
4
+
5
+ This is a proof-of-concept fine-tune of Facebook's OPT-350M model optimized for dialogue, to be used as a stepping stone to higher parameter models.
6
+
7
+ Disclaimer: NSFW data was included in the fine-tuning of this model. Although SFW inputs will usually result in SFW outputs, you are advised to **chat at your own risk. This model is not suitable for use by minors.**
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "opt-350m",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 2,
10
+ "do_layer_norm_before": false,
11
+ "dropout": 0.1,
12
+ "eos_token_id": 2,
13
+ "ffn_dim": 4096,
14
+ "hidden_size": 1024,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "opt",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.20.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 50272,
27
+ "word_embed_proj_dim": 512
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pygmalion-350m.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d55524d550fb87ac9b9a9509c97016d5ad20b4e8a87e8ac355f07c9bd21048
3
+ size 1324913007
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"errors": "replace", "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "patrickvonplaten/opt-30b"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff