Upload main model (test)

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
This commit is contained in:
Tear Gosling 2022-12-20 22:15:03 +00:00 committed by huggingface-web
parent 4c489e14d9
commit 0afbe0ce28
7 changed files with 50042 additions and 3 deletions

View File

@ -1,3 +1,7 @@
--- # pygmalion-350m
license: other
--- # Model description
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.
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.**

28
config.json Normal file
View File

@ -0,0 +1,28 @@
{
"_name_or_path": "opt-350m",
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"do_layer_norm_before": false,
"dropout": 0.1,
"eos_token_id": 2,
"ffn_dim": 4096,
"hidden_size": 1024,
"init_std": 0.02,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"prefix": "</s>",
"torch_dtype": "float16",
"transformers_version": "4.20.0.dev0",
"use_cache": true,
"vocab_size": 50272,
"word_embed_proj_dim": 512
}

50001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
pygmalion-350m.bin Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0d55524d550fb87ac9b9a9509c97016d5ad20b4e8a87e8ac355f07c9bd21048
size 1324913007

1
special_tokens_map.json Normal file
View File

@ -0,0 +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}}

1
tokenizer_config.json Normal file
View File

@ -0,0 +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"}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long