初始化项目,由ModelHub XC社区提供模型

Model: PygmalionAI/pygmalion-350m
Source: Original Platform
This commit is contained in:
ModelHub XC committed 2026-05-20 11:46:38 +08:00
commit 62f7251eb4
9 files changed
+50109

No files matched your search

+49
View File
@@ -0,0 +1,49 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+24
View File
@@ -0,0 +1,24 @@
---
language:
- en
thumbnail:
tags:
- convAI
- conversational
inference: false
---
# pygmalion-350m
# 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.**
# Fine-tuning process
This model was much easier than expected to create.
We used the [ColossalAI](https://www.colossalai.org/) library to fine-tune the [OPT-350M](https://huggingface.co/facebook/opt-350m) model originally trained by Facebook on The Pile. Though our initial dataset was sets of dialogue gathered from various sources totaling about 50 MB in size, early training runs revealed that the model converged after only 7% of the dataset was passed through. To alleviate this, we massively reduced the size of the dataset to only 273 KB.
ColossalAI's magic allowed for something incredible: this entire model was fine-tuned on a singular GPU with only 6 GB ***(!)*** of VRAM. Fine-tuning took less than an hour to complete.
+28
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
}
+1
View File
@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
+50001
View File
File diff suppressed because it is too large. Load diff
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:356aa4ab61193d13e3e7a097bb5f2c025dc2536d5f127154889202ba3c735ae2
size 1324917213
+1
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
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
View File
@@ -0,0 +1 @@
{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, ".": 4, "Ġthe": 5, ",": 6, "Ġto": 7, "Ġand": 8, "Ġof": 9, "Ġa": 10, "Ġin": 11, "-": 12, "Ġfor": 13, "Ġthat": 14, "Ġon": 15, "Ġis": 16, "âĢ": 17, "'s": 18, "Ġwith": 19, "ĠThe": 20, "Ġwas": 21, "Ġ\"": 22, "Ġat": 23, "Ġit": 24, "Ġas": 25, "Ġsaid": 26, "Ļ": 27, "Ġbe": 28, "s": 29, "Ġby": 30, "Ġfrom": 31, "Ġare": 32, "Ġhave": 33, "Ġhas": 34, ":": 35, "Ġ(": 36, "Ġhe": 37, "ĠI": 38, "Ġhis": 39, "Ġwill": 40, "Ġan": 41, "Ġthis": 42, ")": 43, "ĠâĢ": 44, "Ġnot": 45, "Ŀ": 46, "Ġyou": 47, "ľ": 48, "Ġtheir": 49, "Ġor": 50, "Ġthey": 51, "Ġwe": 52, "Ġbut": 53, "Ġwho": 54, "Ġmore": 55, "Ġhad": 56, "Ġbeen": 57, "Ġwere": 58, "Ġabout": 59, ",\"": 60, "Ġwhich": 61, "Ġup": 62, "Ġits": 63, "Ġcan": 64, "Ġone": 65, "Ġout": 66, "Ġalso": 67, "Ġ$": 68, "Ġher": 69, "Ġall": 70, "Ġafter": 71, ".\"": 72, "/": 73, "Ġwould": 74, "'t": 75, "Ġyear": 76, "Ġwhen": 77, "Ġfirst": 78, "Ġshe": 79, "Ġtwo": 80, "Ġover": 81, "Ġpeople": 82, "ĠA": 83, "Ġour": 84, "ĠIt": 85, "Ġtime": 86, "Ġthan": 87, "Ġinto": 88, "Ġthere": 89, "t": 90, "ĠHe": 91, "Ġnew": 92, "ĠâĢĶ": 93, "Ġlast": 94, "Ġjust": 95, "ĠIn": 96, "Ġother": 97, "Ġso": 98, "Ġwhat": 99, "I": 100, "Ġlike": 101, "a": 102, "Ġsome": 103, "S": 104, "ë": 105, "Ġthem": 106, "Ġyears": 107, "'": 108, "Ġdo": 109, "Ġyour": 110, "Ġ-": 111, "Ġ1": 112, "\"": 113, "Ġif": 114, "Ġcould": 115, "?": 116, "Ġno": 117, "i": 118, "m": 119, "Ġget": 120, "ĠU": 121, "Ġnow": 122, "Ġhim": 123, "Ġback": 124, "ĠBut": 125, "ĠâĢĵ": 126, "Ġmy": 127, "Ġ'": 128, "Ġonly": 129, "Ġthree": 130, ";": 131, "Ġ2": 132, "The": 133, "1": 134, "Ġpercent": 135, "Ġagainst": 136, "Ġbefore": 137, "Ġcompany": 138, "o": 139, "ĠTrump": 140, "Ġhow": 141, "Ġbecause": 142, "Ġany": 143, "Ġmost": 144, "Ġbeing": 145, "Ġmake": 146, "Ġwhere": 147, "Ġduring": 148, "Ġthrough": 149, "Ġwhile": 150, "000": 151, "ĠThis": 152, "Ġmillion": 153, "ing": 154, "Ġ3": 155, "Ġmade": 156, "Ġwell": 157, "Ġ10": 158, "Ġdown": 159, "Ġoff": 160, "Ġsays": 161, "Ġme": 162, "ĠB": 163, "Ġgoing": 164, "Ġteam": 165, "ĠWe": 166, "Ġthose": 167, "Ġgovernment": 168, "Ġway": 169, "We": 170, "Ġmany": 171, "Ġthen": 172, "Ġwork": 173, "Ġtold": 174, "com": 175, "2": 176, "Ġgame": 177, "ĠAnd": 178, "in": 179, "year": 180, "Ġp": 181, "Ġvery": 182, "Ġday": 183, "Ġhome": 184, "Ġtake": 185, "Ġweek": 186, "Ġsince": 187, "ĠNew": 188, "Ġmay": 189, "Ġeven": 190, "Ġseason": 191, "Ġsee": 192, "Ġ2017": 193, "Ġstate": 194, "Ġ5": 195, "ed": 196, "Ġshould": 197, "Ġaround": 198, "Ġ2018": 199, "Ġsecond": 200, "Ġus": 201, "Ġstill": 202, "Ġmuch": 203, "Ġ4": 204, "Ġgood": 205, "Ġthink": 206, "%": 207, "ĠS": 208, "Ġthese": 209, "Ġmarket": 210, "ĠD": 211, "th": 212, "Ġgo": 213, "'re": 214, "Ġsuch": 215, "Ġknow": 216, "Ġincluding": 217, "Ġdon": 218, "y": 219, "Ġnext": 220, "ĠP": 221, "Ġdid": 222, "Ġunder": 223, "Ġsay": 224, "en": 225, "ĠL": 226, "Ġbetween": 227, "Ġper": 228, "ĠK": 229, "ĠC": 230, "Ġ6": 231, "Ġworld": 232, "Ġpart": 233, "ĠN": 234, "Ġright": 235, "Ġwant": 236, "Ġfour": 237, "),": 238, "Ġhigh": 239, "Ġneed": 240, "re": 241, "e": 242, "It": 243, "Ġhelp": 244, "5": 245, "3": 246, "Ġcountry": 247, "ĠR": 248, "Ġpolice": 249, "A": 250, "Ġlong": 251, "ĠThey": 252, "Ġend": 253, "er": 254, "ĠT": 255, "ĠM": 256, "u": 257, "Ġboth": 258, "Ġhere": 259, "an": 260, "on": 261, "Ġ7": 262, "Ġde": 263, "ĠShe": 264, "Ġbusiness": 265, "Ġreport": 266, "j": 267, "ers": 268, "Ġreally": 269, "ĠPresident": 270, "ar": 271, "ĠG": 272, "ĠFriday": 273, "ĠF": 274, "Ġbest": 275, "Ġsame": 276, "Ġanother": 277, "Ġset": 278, "old": 279, "ĠThat": 280, "as": 281, "n": 282, "Ġcome": 283, "Ġfamily": 284, "Ġpublic": 285, "ĠFor": 286, "ĠAs": 287, "0": 288, "ĠH": 289, "Ġ8": 290, "Ġ20": 291, "Ġfive": 292, "es": 293, "ĠTuesday": 294, "Ġn": 295, "ĠThursday": 296, "Ġquarter": 297, "h": 298, "Ġtop": 299, "Ġgot": 300, "Ġlife": 301, "ĠMonday": 302, "Ġfound": 303, "Ġuse": 304, "ĠW": 305, "4": 306, "ĠWednesday": 307, "Ġown": 308, "Ġaccording": 309, "Ġplay": 310, "Ġshow": 311, "ĠSt": 312, "Ġman": 313, "Ġleft": 314, "ĠUnited": 315, "Ġ12": 316, "Ġplace": 317, "ĠIf": 318, "Ġlot": 319, "Ġformer": 320, "Ġ0": 321, ").": 322, "Ġsupport": 323, "ie": 324, "Ġbillion": 325, "Ġt": 326, "Ġshares": 327, "!": 328, "z": 329, "k": 330, "ĠState": 331, "Ġpoints": 332, "Ġgroup": 333, "Ġschool": 334, "Ġinformation": 335, "Ġ2016": 336, "al": 337, "r": 338, "Ġwin": 339, "Ġnews": 340, "Ġused": 341, "Ġput": 342, "Ġcity": 343, "ĠJ": 344, "ĠThere": 345, "Ġnumber": 346, "C": 347, "'ve": 348, "Ġeach": 349, "Ġtoo": 350, "Ġwon": 351, "ly": 352, "Ġmonth": 353, "is": 354, "Ġadded": 355, "Ġlook": 356, "Ġbetter": 357, "Ġevery": 358, "Ġ&": 359, "Ġdays": 360, "Ġ9": 361, "Ġtook": 362, "Ġnight": 363, "Ġe": 364, "Ġ11": 365, "os": 366, "Ġfew": 36Line truncated