mirror of
https://github.com/KoboldAI/KoboldAI-Client.git
synced 2025-06-05 21:59:24 +02:00
Merge branch 'UI2' of https://github.com/ebolam/KoboldAI into UI2
This commit is contained in:
ebolam
70
aiserver.py
70
aiserver.py
@@ -77,7 +77,8 @@ try:
|
||||
from transformers.models.opt.modeling_opt import OPTDecoder
|
||||
except:
|
||||
pass
|
||||
import transformers.generation_utils
|
||||
|
||||
from transformers import GenerationMixin
|
||||
|
||||
# Text2img
|
||||
import base64
|
||||
@@ -127,20 +128,20 @@ class use_core_manipulations:
|
||||
old_get_stopping_criteria: callable
|
||||
|
||||
def __enter__(self):
|
||||
use_core_manipulations.old_get_logits_processor = transformers.generation_utils.GenerationMixin._get_logits_processor
|
||||
transformers.generation_utils.GenerationMixin._get_logits_processor = use_core_manipulations.get_logits_processor
|
||||
use_core_manipulations.old_get_logits_processor = transformers.GenerationMixin._get_logits_processor
|
||||
transformers.GenerationMixin._get_logits_processor = use_core_manipulations.get_logits_processor
|
||||
|
||||
use_core_manipulations.old_sample = transformers.generation_utils.GenerationMixin.sample
|
||||
transformers.generation_utils.GenerationMixin.sample = use_core_manipulations.sample
|
||||
use_core_manipulations.old_sample = transformers.GenerationMixin.sample
|
||||
transformers.GenerationMixin.sample = use_core_manipulations.sample
|
||||
|
||||
use_core_manipulations.old_get_stopping_criteria = transformers.generation_utils.GenerationMixin._get_stopping_criteria
|
||||
transformers.generation_utils.GenerationMixin._get_stopping_criteria = use_core_manipulations.get_stopping_criteria
|
||||
use_core_manipulations.old_get_stopping_criteria = transformers.GenerationMixin._get_stopping_criteria
|
||||
transformers.GenerationMixin._get_stopping_criteria = use_core_manipulations.get_stopping_criteria
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc_value, exc_traceback):
|
||||
transformers.generation_utils.GenerationMixin._get_logits_processor = use_core_manipulations.old_get_logits_processor
|
||||
transformers.generation_utils.GenerationMixin.sample = use_core_manipulations.old_sample
|
||||
transformers.generation_utils.GenerationMixin._get_stopping_criteria = use_core_manipulations.old_get_stopping_criteria
|
||||
transformers.GenerationMixin._get_logits_processor = use_core_manipulations.old_get_logits_processor
|
||||
transformers.GenerationMixin.sample = use_core_manipulations.old_sample
|
||||
transformers.GenerationMixin._get_stopping_criteria = use_core_manipulations.old_get_stopping_criteria
|
||||
|
||||
#==================================================================#
|
||||
# Variables & Storage
|
||||
@@ -168,6 +169,7 @@ model_menu = {
|
||||
["Load custom model from Hugging Face", "customhuggingface", "", True],
|
||||
["Adventure Models", "adventurelist", "", True],
|
||||
["Novel Models", "novellist", "", True],
|
||||
["Chat Models", "chatlist", "", True],
|
||||
["NSFW Models", "nsfwlist", "", True],
|
||||
["Untuned OPT", "optlist", "", True],
|
||||
["Untuned GPT-Neo/J", "gptneolist", "", True],
|
||||
@@ -225,9 +227,10 @@ model_menu = {
|
||||
["Return to Main Menu", "mainmenu", "", True],
|
||||
],
|
||||
'chatlist': [
|
||||
["Convo 6B (Chatbot)", "hitomi-team/convo-6B", "16GB", False],
|
||||
["C1 6B (Chatbot)", "hakurei/c1-6B", "16GB", False],
|
||||
["C1 1.3B (Chatbot)", "iokru/c1-1.3B", "6GB", False],
|
||||
["Pygmalion 6B", "PygmalionAI/pygmalion-6b", "16GB", False],
|
||||
["Pygmalion 2.7B", "PygmalionAI/pygmalion-2.7b", "8GB", False],
|
||||
["Pygmalion 1.3B", "PygmalionAI/pygmalion-1.3b", "6GB", False],
|
||||
["Pygmalion 350M", "PygmalionAI/pygmalion-350m", "2GB", False],
|
||||
["Return to Main Menu", "mainmenu", "", True],
|
||||
],
|
||||
'gptneolist': [
|
||||
@@ -314,12 +317,12 @@ model_menu = {
|
||||
["Return to Main Menu", "mainmenu", "", True],
|
||||
],
|
||||
'apilist': [
|
||||
["GooseAI API (requires API key)", "GooseAI", "", False],
|
||||
["OpenAI API (requires API key)", "OAI", "", False],
|
||||
["InferKit API (requires API key)", "InferKit", "", False],
|
||||
["GooseAI API (requires API key)", "GooseAI", "None", False],
|
||||
["OpenAI API (requires API key)", "OAI", "None", False],
|
||||
["InferKit API (requires API key)", "InferKit", "None", False],
|
||||
# ["KoboldAI Server API (Old Google Colab)", "Colab", "", False],
|
||||
["KoboldAI API", "API", "", False],
|
||||
["KoboldAI Horde", "CLUSTER", "", False],
|
||||
["KoboldAI API", "API", "None", False],
|
||||
["KoboldAI Horde", "CLUSTER", "None", False],
|
||||
["Return to Main Menu", "mainmenu", "", True],
|
||||
]
|
||||
}
|
||||
@@ -1493,6 +1496,7 @@ def general_startup(override_args=None):
|
||||
parser.add_argument("--no_aria2", action='store_true', default=False, help="Prevents KoboldAI from using aria2 to download huggingface models more efficiently, in case aria2 is causing you issues")
|
||||
parser.add_argument("--lowmem", action='store_true', help="Extra Low Memory loading for the GPU, slower but memory does not peak to twice the usage")
|
||||
parser.add_argument("--savemodel", action='store_true', help="Saves the model to the models folder even if --colab is used (Allows you to save models to Google Drive)")
|
||||
parser.add_argument("--cacheonly", action='store_true', help="Does not save the model to the models folder when it has been downloaded in the cache")
|
||||
parser.add_argument("--customsettings", help="Preloads arguements from json file. You only need to provide the location of the json file. Use customsettings.json template file. It can be renamed if you wish so that you can store multiple configurations. Leave any settings you want as default as null. Any values you wish to set need to be in double quotation marks")
|
||||
parser.add_argument("--no_ui", action='store_true', default=False, help="Disables the GUI and Socket.IO server while leaving the API server running.")
|
||||
parser.add_argument("--summarizer_model", action='store', default="philschmid/bart-large-cnn-samsum", help="Huggingface model to use for summarization. Defaults to sshleifer/distilbart-cnn-12-6")
|
||||
@@ -2412,7 +2416,7 @@ def patch_transformers():
|
||||
processors.append(PhraseBiasLogitsProcessor())
|
||||
return processors
|
||||
use_core_manipulations.get_logits_processor = new_get_logits_processor
|
||||
new_get_logits_processor.old_get_logits_processor = transformers.generation_utils.GenerationMixin._get_logits_processor
|
||||
new_get_logits_processor.old_get_logits_processor = transformers.GenerationMixin._get_logits_processor
|
||||
|
||||
class KoboldLogitsWarperList(LogitsProcessorList):
|
||||
def __init__(self, beams: int = 1, **kwargs):
|
||||
@@ -2447,15 +2451,15 @@ def patch_transformers():
|
||||
kwargs.setdefault("pad_token_id", 2)
|
||||
return new_sample.old_sample(self, *args, **kwargs)
|
||||
|
||||
new_sample.old_sample = transformers.generation_utils.GenerationMixin.sample
|
||||
new_sample.old_sample = transformers.GenerationMixin.sample
|
||||
use_core_manipulations.sample = new_sample
|
||||
|
||||
# Allow bad words filter to ban <|endoftext|> token
|
||||
import transformers.generation_logits_process
|
||||
import transformers.generation.logits_process
|
||||
def new_init(self, bad_words_ids: List[List[int]], eos_token_id: int):
|
||||
return new_init.old_init(self, bad_words_ids, -1)
|
||||
new_init.old_init = transformers.generation_logits_process.NoBadWordsLogitsProcessor.__init__
|
||||
transformers.generation_logits_process.NoBadWordsLogitsProcessor.__init__ = new_init
|
||||
new_init.old_init = transformers.generation.logits_process.NoBadWordsLogitsProcessor.__init__
|
||||
transformers.generation.logits_process.NoBadWordsLogitsProcessor.__init__ = new_init
|
||||
|
||||
class TokenStreamer(StoppingCriteria):
|
||||
# A StoppingCriteria is used here because it seems to run after
|
||||
@@ -2474,9 +2478,6 @@ def patch_transformers():
|
||||
|
||||
if not koboldai_vars.output_streaming:
|
||||
return False
|
||||
|
||||
if koboldai_vars.chatmode:
|
||||
return False
|
||||
|
||||
data = [applyoutputformatting(utils.decodenewlines(tokenizer.decode(x[-1])), no_sentence_trimming=True, no_single_line=True) for x in input_ids]
|
||||
koboldai_vars.actions.stream_tokens(data)
|
||||
@@ -2616,7 +2617,7 @@ def patch_transformers():
|
||||
return False
|
||||
|
||||
|
||||
old_get_stopping_criteria = transformers.generation_utils.GenerationMixin._get_stopping_criteria
|
||||
old_get_stopping_criteria = transformers.GenerationMixin._get_stopping_criteria
|
||||
|
||||
def new_get_stopping_criteria(self, *args, **kwargs):
|
||||
global tokenizer
|
||||
@@ -3194,7 +3195,7 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
|
||||
torch._utils._rebuild_tensor = old_rebuild_tensor
|
||||
|
||||
if not args.colab or args.savemodel:
|
||||
if not (args.colab or args.cacheonly) or args.savemodel:
|
||||
import shutil
|
||||
tokenizer.save_pretrained("models/{}".format(koboldai_vars.model.replace('/', '_')))
|
||||
if(koboldai_vars.fp32_model and ("breakmodel" not in globals() or not breakmodel.disk_blocks)): # Use save_pretrained to convert fp32 models to fp16, unless we are using disk cache because save_pretrained is not supported in that case
|
||||
@@ -3210,7 +3211,10 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.configuration_utils.CONFIG_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), transformers.configuration_utils.CONFIG_NAME))
|
||||
if(utils.num_shards is None):
|
||||
# Save the pytorch_model.bin of an unsharded model
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
|
||||
try:
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
|
||||
except:
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, "model.safetensors", revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), "model.safetensors"))
|
||||
else:
|
||||
with open(utils.from_pretrained_index_filename) as f:
|
||||
map_data = json.load(f)
|
||||
@@ -6473,7 +6477,7 @@ def getnewcontent(txt):
|
||||
#==================================================================#
|
||||
def applyinputformatting(txt):
|
||||
# Add sentence spacing
|
||||
if(koboldai_vars.frmtadsnsp):
|
||||
if(koboldai_vars.frmtadsnsp and not koboldai_vars.chatmode):
|
||||
txt = utils.addsentencespacing(txt, koboldai_vars)
|
||||
|
||||
return txt
|
||||
@@ -6507,9 +6511,11 @@ def applyoutputformatting(txt, no_sentence_trimming=False, no_single_line=False)
|
||||
if(koboldai_vars.frmtrmspch):
|
||||
txt = utils.removespecialchars(txt, koboldai_vars)
|
||||
# Single Line Mode
|
||||
if((koboldai_vars.singleline or koboldai_vars.chatmode) and not no_single_line):
|
||||
if(koboldai_vars.singleline and not no_single_line):
|
||||
txt = utils.singlelineprocessing(txt, koboldai_vars)
|
||||
|
||||
# Chat Mode Trimming
|
||||
if(koboldai_vars.chatmode):
|
||||
txt = utils.chatmodeprocessing(txt, koboldai_vars)
|
||||
for sub in koboldai_vars.substitutions:
|
||||
if not sub["enabled"]:
|
||||
continue
|
||||
|
||||
@@ -5,8 +5,7 @@
|
||||
"colab": {
|
||||
"name": "ColabKobold GPU",
|
||||
"private_outputs": true,
|
||||
"provenance": [],
|
||||
"include_colab_link": true
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
@@ -18,16 +17,6 @@
|
||||
"accelerator": "GPU"
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "view-in-github",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/KoboldAI/KoboldAI-Client/blob/main/colab/GPU.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
@@ -82,7 +71,7 @@
|
||||
"#@title <b><-- Select your model below and then click this to start KoboldAI</b>\n",
|
||||
"#@markdown You can find a description of the models below along with instructions on how to start KoboldAI.\n",
|
||||
"\n",
|
||||
"Model = \"Nerys V2 6B\" #@param [\"Nerys V2 6B\", \"Erebus 6B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Lit V2 6B\", \"Lit 6B\", \"Shinen 6B\", \"Nerys 2.7B\", \"AID 2.7B\", \"Erebus 2.7B\", \"Janeway 2.7B\", \"Picard 2.7B\", \"Horni LN 2.7B\", \"Horni 2.7B\", \"Shinen 2.7B\", \"OPT 2.7B\", \"Fairseq Dense 2.7B\", \"Neo 2.7B\"] {allow-input: true}\n",
|
||||
"Model = \"Nerys V2 6B\" #@param [\"Nerys V2 6B\", \"Erebus 6B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Pygmalion 6B\", \"Lit V2 6B\", \"Lit 6B\", \"Shinen 6B\", \"Nerys 2.7B\", \"AID 2.7B\", \"Erebus 2.7B\", \"Janeway 2.7B\", \"Picard 2.7B\", \"Horni LN 2.7B\", \"Horni 2.7B\", \"Shinen 2.7B\", \"OPT 2.7B\", \"Fairseq Dense 2.7B\", \"Neo 2.7B\"] {allow-input: true}\n",
|
||||
"Version = \"Official\" #@param [\"Official\", \"United\"] {allow-input: true}\n",
|
||||
"Provider = \"Localtunnel\" #@param [\"Localtunnel\", \"Cloudflare\"]\n",
|
||||
"use_google_drive = True #@param {type:\"boolean\"}\n",
|
||||
@@ -118,6 +107,10 @@
|
||||
" Model = \"KoboldAI/GPT-J-6B-Adventure\"\n",
|
||||
" path = \"\"\n",
|
||||
" download = \"\"\n",
|
||||
"elif Model == \"Pygmalion 6B\":\n",
|
||||
" Model = \"PygmalionAI/pygmalion-6b\"\n",
|
||||
" path = \"\"\n",
|
||||
" download = \"\"\n",
|
||||
"elif Model == \"Lit V2 6B\":\n",
|
||||
" Model = \"hakurei/litv2-6B-rev3\"\n",
|
||||
" path = \"\"\n",
|
||||
@@ -196,6 +189,7 @@
|
||||
"| [Janeway](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-Janeway) by Mr Seeker | Novel | Janeway is a model created from Picard's dataset combined with a brand new collection of ebooks. This model is trained on 20% more content than Picard and has been trained on literature from various genres. Although the model is mainly focussed on SFW, romantic scenes might involve a degree of nudity. |\n",
|
||||
"| [Picard](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-Picard) by Mr Seeker | Novel | Picard is a model trained for SFW Novels based on Neo 2.7B. It is focused on Novel style writing without the NSFW bias. While the name suggests a sci-fi model this model is designed for Novels of a variety of genre's. It is meant to be used in KoboldAI's regular mode. |\n",
|
||||
"| [AID](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-AID) by melastacho | Adventure | Also know as Adventure 2.7B this is a clone of the AI Dungeon Classic model and is best known for the epic wackey adventures that AI Dungeon Classic players love. |\n",
|
||||
"| [Pygmalion](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by PygmalionAI | Chatbot | Pygmalion is a chat model that has been based on a few models that came before it. First the model originates from LitV2, it was then trained by Haru on a chat dataset to create ConvoGPT. ConvoGPT was then trained by PygmalionAI on chat data that contains longer responses and emotions. Making for a higher quality chat experience than you can get from other models such as Erebus that are not directly trained on chatting. |\n",
|
||||
"| [Horni LN](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-Horni-LN) by finetune | Novel | This model is based on Horni 2.7B and retains its NSFW knowledge, but was then further biased towards SFW novel stories. If you seek a balance between a SFW Novel model and a NSFW model this model should be a good choice. |\n",
|
||||
"| [Horni](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-Horni) by finetune | NSFW | This model is tuned on Literotica to produce a Novel style model biased towards NSFW content. Can still be used for SFW stories but will have a bias towards NSFW content. It is meant to be used in KoboldAI's regular mode. |\n",
|
||||
"| [Shinen](https://huggingface.co/KoboldAI/GPT-Neo-2.7B-Shinen) by Mr Seeker | NSFW | Shinen is an alternative to the Horni model designed to be more explicit. If Horni is to tame for you Shinen might produce better results. While it is a Novel model it is unsuitable for SFW stories due to its heavy NSFW bias. Shinen will not hold back. It is meant to be used in KoboldAI's regular mode. |\n",
|
||||
@@ -213,6 +207,7 @@
|
||||
"| [Shinen](https://huggingface.co/KoboldAI/fairseq-dense-13B-Shinen) by Mr Seeker | NSFW | Shinen is an NSFW model trained on a variety of stories from the website Sexstories it contains many different kinks. It has been merged into the larger (and better) Erebus model. |\n",
|
||||
"| [Skein](https://huggingface.co/KoboldAI/GPT-J-6B-Skein) by VE\\_FORBRYDERNE | Adventure | Skein is best used with Adventure mode enabled, it consists of a 4 times larger adventure dataset than the Adventure model making it excellent for text adventure gaming. On top of that it also consists of light novel training further expanding its knowledge and writing capabilities. It can be used with the You filter bias if you wish to write Novels with it, but dedicated Novel models can perform better for this task. |\n",
|
||||
"| [Adventure](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by VE\\_FORBRYDERNE | Adventure | Adventure is a 6B model designed to mimick the behavior of AI Dungeon. It is exclusively for Adventure Mode and can take you on the epic and wackey adventures that AI Dungeon players love. It also features the many tropes of AI Dungeon as it has been trained on very similar data. It must be used in second person (You). |\n",
|
||||
"| [Pygmalion](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by PygmalionAI | Chatbot | Pygmalion is a chat model that has been based on a few models that came before it. First the model originates from LitV2, it was then trained by Haru on a chat dataset to create ConvoGPT. ConvoGPT was then trained by PygmalionAI on chat data that contains longer responses and emotions. Making for a higher quality chat experience than you can get from other models such as Erebus that are not directly trained on chatting. |\n",
|
||||
"| [Lit](https://huggingface.co/hakurei/lit-6B) ([V2](https://huggingface.co/hakurei/litv2-6B-rev3)) by Haru | NSFW | Lit is a great NSFW model trained by Haru on both a large set of Literotica stories and high quality novels along with tagging support. Creating a high quality model for your NSFW stories. This model is exclusively a novel model and is best used in third person. |\n",
|
||||
"| [OPT](https://huggingface.co/facebook/opt-13b) by Metaseq | Generic | OPT is considered one of the best base models as far as content goes, its behavior has the strengths of both GPT-Neo and Fairseq Dense. Compared to Neo duplicate and unnecessary content has been left out, while additional literature was added in similar to the Fairseq Dense model. The Fairseq Dense model however lacks the broader data that OPT does have. The biggest downfall of OPT is its license, which prohibits any commercial usage, or usage beyond research purposes. |\n",
|
||||
"| [Neo(X)](https://huggingface.co/EleutherAI/gpt-neox-20b) by EleutherAI | Generic | NeoX is the largest EleutherAI model currently available, being a generic model it is not particularly trained towards anything and can do a variety of writing, Q&A and coding tasks. 20B's performance is closely compared to the 13B models and it is worth trying both especially if you have a task that does not involve english writing. Its behavior will be similar to the GPT-J-6B model since they are trained on the same dataset but with more sensitivity towards repetition penalty and with more knowledge. |\n",
|
||||
|
||||
@@ -66,10 +66,10 @@
|
||||
"#@title <b><-- Select your model below and then click this to start KoboldAI</b>\n",
|
||||
"#@markdown You can find a description of the models below along with instructions on how to start KoboldAI.\n",
|
||||
"\n",
|
||||
"Model = \"Nerys 13B V2\" #@param [\"Nerys 13B V2\", \"Erebus 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 20B\", \"Erebus 20B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Lit V2 6B\", \"Lit 6B\", \"NeoX 20B\", \"OPT 13B\", \"Fairseq Dense 13B\", \"GPT-J-6B\"] {allow-input: true}\n",
|
||||
"Model = \"Nerys 13B V2\" #@param [\"Nerys 13B V2\", \"Erebus 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 20B\", \"Erebus 20B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Pygmalion 6B\", \"Lit V2 6B\", \"Lit 6B\", \"NeoX 20B\", \"OPT 13B\", \"Fairseq Dense 13B\", \"GPT-J-6B\"] {allow-input: true}\n",
|
||||
"Version = \"Official\" #@param [\"Official\", \"United\"] {allow-input: true}\n",
|
||||
"Provider = \"Localtunnel\" #@param [\"Localtunnel\", \"Cloudflare\"]\n",
|
||||
"use_google_drive = True #@param {type:\"boolean\"}\n",
|
||||
"use_google_drive = True #@param {type:\"boolean\"}\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"try:\n",
|
||||
@@ -81,13 +81,13 @@
|
||||
"print('Now we will need your Google Drive to store settings and saves, you must login with the same account you used for Colab.')\n",
|
||||
"from google.colab import drive\n",
|
||||
"if use_google_drive:\n",
|
||||
" drive.mount('/content/drive/')\n",
|
||||
"else:\n",
|
||||
" import os\n",
|
||||
" if not os.path.exists(\"/content/drive\"):\n",
|
||||
" os.mkdir(\"/content/drive\")\n",
|
||||
" if not os.path.exists(\"/content/drive/MyDrive/\"):\n",
|
||||
" os.mkdir(\"/content/drive/MyDrive/\")\n",
|
||||
" drive.mount('/content/drive/')\n",
|
||||
"else:\n",
|
||||
" import os\n",
|
||||
" if not os.path.exists(\"/content/drive\"):\n",
|
||||
" os.mkdir(\"/content/drive\")\n",
|
||||
" if not os.path.exists(\"/content/drive/MyDrive/\"):\n",
|
||||
" os.mkdir(\"/content/drive/MyDrive/\")\n",
|
||||
"\n",
|
||||
"if Model == \"Janeway 13B\":\n",
|
||||
" Model = \"KoboldAI/fairseq-dense-13B-Janeway\"\n",
|
||||
@@ -129,6 +129,10 @@
|
||||
" Model = \"KoboldAI/GPT-J-6B-Adventure\"\n",
|
||||
" path = \"\"\n",
|
||||
" download = \"\"\n",
|
||||
"elif Model == \"Pygmalion 6B\":\n",
|
||||
" Model = \"PygmalionAI/pygmalion-6b\"\n",
|
||||
" path = \"\"\n",
|
||||
" download = \"\"\n",
|
||||
"elif Model == \"Lit V2 6B\":\n",
|
||||
" Model = \"hakurei/litv2-6B-rev3\"\n",
|
||||
" path = \"\"\n",
|
||||
@@ -178,6 +182,7 @@
|
||||
"| [Shinen](https://huggingface.co/KoboldAI/fairseq-dense-13B-Shinen) by Mr Seeker | NSFW | Shinen is an NSFW model trained on a variety of stories from the website Sexstories it contains many different kinks. It has been merged into the larger (and better) Erebus model. |\n",
|
||||
"| [Skein](https://huggingface.co/KoboldAI/GPT-J-6B-Skein) by VE\\_FORBRYDERNE | Adventure | Skein is best used with Adventure mode enabled, it consists of a 4 times larger adventure dataset than the Adventure model making it excellent for text adventure gaming. On top of that it also consists of light novel training further expanding its knowledge and writing capabilities. It can be used with the You filter bias if you wish to write Novels with it, but dedicated Novel models can perform better for this task. |\n",
|
||||
"| [Adventure](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by VE\\_FORBRYDERNE | Adventure | Adventure is a 6B model designed to mimick the behavior of AI Dungeon. It is exclusively for Adventure Mode and can take you on the epic and wackey adventures that AI Dungeon players love. It also features the many tropes of AI Dungeon as it has been trained on very similar data. It must be used in second person (You). |\n",
|
||||
"| [Pygmalion](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by PygmalionAI | Chatbot | Pygmalion is a chat model that has been based on a few models that came before it. First the model originates from LitV2, it was then trained by Haru on a chat dataset to create ConvoGPT. ConvoGPT was then trained by PygmalionAI on chat data that contains longer responses and emotions. Making for a higher quality chat experience than you can get from other models such as Erebus that are not directly trained on chatting. |\n",
|
||||
"| [Lit](https://huggingface.co/hakurei/lit-6B) ([V2](https://huggingface.co/hakurei/litv2-6B-rev3)) by Haru | NSFW | Lit is a great NSFW model trained by Haru on both a large set of Literotica stories and high quality novels along with tagging support. Creating a high quality model for your NSFW stories. This model is exclusively a novel model and is best used in third person. |\n",
|
||||
"| [OPT](https://huggingface.co/facebook/opt-13b) by Metaseq | Generic | OPT is considered one of the best base models as far as content goes, its behavior has the strengths of both GPT-Neo and Fairseq Dense. Compared to Neo duplicate and unnecessary content has been left out, while additional literature was added in similar to the Fairseq Dense model. The Fairseq Dense model however lacks the broader data that OPT does have. The biggest downfall of OPT is its license, which prohibits any commercial usage, or usage beyond research purposes. |\n",
|
||||
"| [Neo(X)](https://huggingface.co/EleutherAI/gpt-neox-20b) by EleutherAI | Generic | NeoX is the largest EleutherAI model currently available, being a generic model it is not particularly trained towards anything and can do a variety of writing, Q&A and coding tasks. 20B's performance is closely compared to the 13B models and it is worth trying both especially if you have a task that does not involve english writing. Its behavior will be similar to the GPT-J-6B model since they are trained on the same dataset but with more sensitivity towards repetition penalty and with more knowledge. |\n",
|
||||
@@ -240,7 +245,6 @@
|
||||
"name": "ColabKobold TPU",
|
||||
"provenance": [],
|
||||
"private_outputs": true,
|
||||
"collapsed_sections": [],
|
||||
"include_colab_link": true
|
||||
},
|
||||
"kernelspec": {
|
||||
|
||||
@@ -6,4 +6,4 @@ WORKDIR /content/
|
||||
COPY env.yml /home/micromamba/env.yml
|
||||
RUN micromamba install -y -n base -f /home/micromamba/env.yml
|
||||
USER root
|
||||
RUN apt update && apt install xorg -y
|
||||
RUN apt update && apt install xorg aria2 -y
|
||||
|
||||
@@ -3,4 +3,4 @@ WORKDIR /content/
|
||||
COPY env.yml /home/micromamba/env.yml
|
||||
RUN micromamba install -y -n base -f /home/micromamba/env.yml
|
||||
USER root
|
||||
RUN apt update && apt install xorg libsqlite3-0 -y
|
||||
RUN apt update && apt install xorg libsqlite3-0 aria2 -y
|
||||
|
||||
@@ -11,6 +11,7 @@ dependencies:
|
||||
- python=3.8.*
|
||||
- cudatoolkit=11.1
|
||||
- eventlet
|
||||
- dnspython=2.2.1
|
||||
- markdown
|
||||
- bleach=4.1.0
|
||||
- pip
|
||||
@@ -27,7 +28,7 @@ dependencies:
|
||||
- flask-cloudflared
|
||||
- flask-ngrok
|
||||
- lupa==1.10
|
||||
- transformers==4.24.0
|
||||
- transformers==4.25.1
|
||||
- huggingface_hub>=0.10.1
|
||||
- safetensors
|
||||
- accelerate
|
||||
|
||||
@@ -8,6 +8,7 @@ dependencies:
|
||||
- flask-session
|
||||
- python=3.8.*
|
||||
- eventlet
|
||||
- dnspython=2.2.1
|
||||
- markdown
|
||||
- bleach=4.1.0
|
||||
- pip
|
||||
@@ -22,11 +23,11 @@ dependencies:
|
||||
- psutil
|
||||
- pip:
|
||||
- --extra-index-url https://download.pytorch.org/whl/rocm5.1.1
|
||||
- torch==1.11.*
|
||||
- torch==1.12.1+rocm5.1.1
|
||||
- flask-cloudflared
|
||||
- flask-ngrok
|
||||
- lupa==1.10
|
||||
- transformers==4.24.0
|
||||
- transformers==4.25.1
|
||||
- huggingface_hub>=0.10.1
|
||||
- safetensors
|
||||
- accelerate
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
transformers==4.24.0
|
||||
transformers==4.25.1
|
||||
huggingface_hub>=0.10.1
|
||||
Flask
|
||||
Flask-SocketIO
|
||||
@@ -7,6 +7,7 @@ torch >= 1.9, < 1.13
|
||||
flask-cloudflared
|
||||
flask-ngrok
|
||||
eventlet
|
||||
dnspython==2.2.1
|
||||
lupa==1.10
|
||||
markdown
|
||||
bleach==4.1.0
|
||||
|
||||
@@ -5,7 +5,7 @@ requests
|
||||
dm-haiku == 0.0.5
|
||||
jax == 0.2.21
|
||||
jaxlib >= 0.1.69, <= 0.3.7
|
||||
transformers == 4.24.0
|
||||
transformers == 4.25.1
|
||||
huggingface_hub >= 0.10.1
|
||||
progressbar2
|
||||
git+https://github.com/VE-FORBRYDERNE/mesh-transformer-jax@ck
|
||||
@@ -14,6 +14,7 @@ Flask-SocketIO
|
||||
flask-cloudflared >= 0.0.5
|
||||
flask-ngrok
|
||||
eventlet
|
||||
dnspython==2.2.1
|
||||
lupa==1.10
|
||||
markdown
|
||||
bleach==4.1.0
|
||||
|
||||
@@ -1941,7 +1941,7 @@ body {
|
||||
|
||||
}
|
||||
|
||||
.popup .model_item {
|
||||
#modelspecifier, .popup .model_item {
|
||||
width: 98%;
|
||||
background-color: var(--popup_item_color);
|
||||
color: var(--popup_item_color_text);
|
||||
@@ -2089,14 +2089,24 @@ body {
|
||||
}
|
||||
/*----------------------------- Model Load Popup ------------------------------------------*/
|
||||
|
||||
.popup_list_area .model_item .model {
|
||||
#specspan, .popup_list_area .model_item .model {
|
||||
grid-area: file;
|
||||
display: grid;
|
||||
grid-template-areas: "item gpu_size";
|
||||
grid-template-columns: auto 40px;
|
||||
grid-template-columns: auto 95px;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
#specspan {
|
||||
grid-template-columns: auto 100px !important;
|
||||
cursor: auto !important;
|
||||
}
|
||||
|
||||
#model-spec-usage {
|
||||
position: relative;
|
||||
left: -20px;
|
||||
}
|
||||
|
||||
.popup .model_item:hover {
|
||||
background-color: var(--popup_hover_color);
|
||||
color: var(--popup_hover_color_text);
|
||||
|
||||
@@ -1607,6 +1607,16 @@ function show_model_menu(data) {
|
||||
} else {
|
||||
document.getElementById("custommodelname").classList.add("hidden");
|
||||
}
|
||||
|
||||
|
||||
// detect if we are in a model selection screen and show the reference
|
||||
var refelement = document.getElementById("modelspecifier");
|
||||
var check = document.getElementById("mainmenu");
|
||||
if (check) {
|
||||
refelement.classList.remove("hidden");
|
||||
} else {
|
||||
refelement.classList.add("hidden");
|
||||
}
|
||||
|
||||
openPopup("load-model");
|
||||
}
|
||||
@@ -7280,4 +7290,15 @@ async function screenshot_selection(summonEvent) {
|
||||
let endDebt = totalText.indexOf(selectionContent) + selectionContent.length;
|
||||
|
||||
await showScreenshotWizard(actionComposition, startDebt=startDebt, endDebt=endDebt, totalText);
|
||||
}
|
||||
}
|
||||
|
||||
$el("#gamescreen").addEventListener("paste", function(event) {
|
||||
// Get rid of rich text, it messes with actions. Not a great fix since it
|
||||
// relies on execCommand but it'll have to do
|
||||
event.preventDefault();
|
||||
document.execCommand(
|
||||
"insertHTML",
|
||||
false,
|
||||
event.clipboardData.getData("text/plain")
|
||||
);
|
||||
});
|
||||
@@ -40,6 +40,12 @@
|
||||
<div class="title">
|
||||
Select A Model To Load
|
||||
</div>
|
||||
<span class="model_item" id="modelspecifier">
|
||||
<span id="specspan">
|
||||
<div id="model-spec-name">Name</div>
|
||||
<div id="model-spec-usage">Usage (VRAM)</div>
|
||||
</span>
|
||||
</span>
|
||||
<div id="loadmodellistbreadcrumbs">
|
||||
|
||||
</div>
|
||||
|
||||
18
utils.py
18
utils.py
@@ -147,6 +147,24 @@ def singlelineprocessing(txt, koboldai_vars):
|
||||
txt = txt + "\n"
|
||||
return txt
|
||||
|
||||
def chatmodeprocessing(txt, koboldai_vars):
|
||||
chatregex = re.compile(r'%s:[.|\n|\W|\w]*'%koboldai_vars.chatname)
|
||||
txt = chatregex.sub('', txt)
|
||||
if(len(koboldai_vars.actions) > 0):
|
||||
if(len(koboldai_vars.actions[-1]) > 0):
|
||||
action = koboldai_vars.actions[-1]
|
||||
lastchar = action[-1] if len(action) else ""
|
||||
else:
|
||||
# Last action is blank, this should never happen, but
|
||||
# since it did let's bail out.
|
||||
return txt
|
||||
else:
|
||||
action = koboldai_vars.prompt
|
||||
lastchar = action[-1] if len(action) else ""
|
||||
if(lastchar != "\n"):
|
||||
txt = txt + "\n"
|
||||
return txt
|
||||
|
||||
#==================================================================#
|
||||
# Cleans string for use in file name
|
||||
#==================================================================#
|
||||
|
||||
Reference in New Issue
Block a user