wanzin commited on
Commit
7bcc472
·
1 Parent(s): b61fd90

adding opt350m model configurations

Browse files
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
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.27.0.dev0"
7
+ }
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:a5223ae6f3c26c6d90003f96a6bcd9a4aaaef0d36fca6469112efeeb985f2842
3
+ size 662513657
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