zishuo/gpt4free
1
0
Fork 0
mirror of https://github.com/xtekky/gpt4free.git synced 2025-10-23 00:09:34 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
a358b28f4762b11d0d398cab134770787ea36e18
gpt4free/g4f/models.py
kqlio67 a358b28f47 Major Provider Updates and Model Support Enhancements (#2467) 
* refactor(g4f/Provider/Airforce.py): improve model handling and filtering

- Add hidden_models set to exclude specific models
- Add evil alias for uncensored model handling
- Extend filtering for model-specific response tokens
- Add response buffering for streamed content
- Update model fetching with error handling

* refactor(g4f/Provider/Blackbox.py): improve caching and model handling

- Add caching system for validated values with file-based storage
- Rename 'flux' model to 'ImageGeneration' and update references
- Add temperature, top_p and max_tokens parameters to generator
- Simplify HTTP headers and remove redundant options
- Add model alias mapping for ImageGeneration
- Add file system utilities for cache management

* feat(g4f/Provider/RobocodersAPI.py): add caching and error handling

- Add file-based caching system for access tokens and sessions
- Add robust error handling with specific error messages
- Add automatic dialog continuation on resource limits
- Add HTML parsing with BeautifulSoup for token extraction
- Add debug logging for error tracking
- Add timeout configuration for API requests

* refactor(g4f/Provider/DarkAI.py): update DarkAI default model and aliases

- Change default model from llama-3-405b to llama-3-70b
- Remove llama-3-405b from supported models list
- Remove llama-3.1-405b from model aliases

* feat(g4f/Provider/Blackbox2.py): add image generation support

- Add image model 'flux' with dedicated API endpoint
- Refactor generator to support both text and image outputs
- Extract headers into reusable static method
- Add type hints for AsyncGenerator return type
- Split generation logic into _generate_text and _generate_image methods
- Add ImageResponse handling for image generation results

BREAKING CHANGE: create_async_generator now returns AsyncGenerator instead of AsyncResult

* refactor(g4f/Provider/ChatGptEs.py): update ChatGptEs model configuration

- Update models list to include gpt-3.5-turbo
- Remove chatgpt-4o-latest from supported models
- Remove model_aliases mapping for gpt-4o

* feat(g4f/Provider/DeepInfraChat.py): add Accept-Language header support

- Add Accept-Language header for internationalization
- Maintain existing header configuration
- Improve request compatibility with language preferences

* refactor(g4f/Provider/needs_auth/Gemini.py): add ProviderModelMixin inheritance

- Add ProviderModelMixin to class inheritance
- Import ProviderModelMixin from base_provider
- Move BaseConversation import to base_provider imports

* refactor(g4f/Provider/Liaobots.py): update model details and aliases

- Add version suffix to o1 model IDs
- Update model aliases for o1-preview and o1-mini
- Standardize version format across model definitions

* refactor(g4f/Provider/PollinationsAI.py): enhance model support and generation

- Split generation logic into dedicated image/text methods
- Add additional text models including sur and claude
- Add width/height parameters for image generation
- Add model existence validation
- Add hasattr checks for model lists initialization

* chore(gitignore): add provider cache directory

- Add g4f/Provider/.cache to gitignore patterns

* refactor(g4f/Provider/ReplicateHome.py): update model configuration

- Update default model to gemma-2b-it
- Add default_image_model configuration
- Remove llava-13b from supported models
- Simplify request headers

* feat(g4f/models.py): expand provider and model support

- Add new providers DarkAI and PollinationsAI
- Add new models for Mistral, Flux and image generation
- Update provider lists for existing models
- Add P1 and Evil models with experimental providers

BREAKING CHANGE: Remove llava-13b model support

* refactor(Airforce): Update type hint for split_message return

- Change return type of  from  to  for consistency with import.
- Maintain overall functionality and structure of the  class.
- Ensure compatibility with type hinting standards in Python.

* refactor(g4f/Provider/Airforce.py): Update type hint for split_message return

- Change return type of 'split_message' from 'list[str]' to 'List[str]' for consistency with import.
- Maintain overall functionality and structure of the 'Airforce' class.
- Ensure compatibility with type hinting standards in Python.

* feat(g4f/Provider/RobocodersAPI.py): Add support for optional BeautifulSoup dependency

- Introduce a check for the BeautifulSoup library and handle its absence gracefully.
- Raise a  if BeautifulSoup is not installed, prompting the user to install it.
- Remove direct import of BeautifulSoup to avoid import errors when the library is missing.

---------

Co-authored-by: kqlio67 <>
2024-12-08 04:43:51 +01:00

928 lines
20 KiB
Python
Raw Blame History

from __future__ import annotations
from dataclasses import dataclass
from .Provider import IterListProvider, ProviderType
from .Provider import (
AIChatFree,
AmigoChat,
Blackbox,
Blackbox2,
BingCreateImages,
ChatGpt,
ChatGptEs,
Cloudflare,
Copilot,
CopilotAccount,
DarkAI,
DDG,
DeepInfraChat,
Free2GPT,
GigaChat,
Gemini,
GeminiPro,
HuggingChat,
HuggingFace,
Liaobots,
Airforce,
MagickPen,
Mhystical,
MetaAI,
MicrosoftDesigner,
OpenaiChat,
OpenaiAccount,
PerplexityLabs,
Pi,
Pizzagpt,
PollinationsAI,
Reka,
ReplicateHome,
RubiksAI,
TeachAnything,
Upstage,
Flux,
)
@dataclass(unsafe_hash=True)
class Model:
"""
Represents a machine learning model configuration.
Attributes:
name (str): Name of the model.
base_provider (str): Default provider for the model.
best_provider (ProviderType): The preferred provider for the model, typically with retry logic.
"""
name: str
base_provider: str
best_provider: ProviderType = None
@staticmethod
def __all__() -> list[str]:
"""Returns a list of all model names."""
return _all_models
class ImageModel(Model):
pass
### Default ###
default = Model(
name = "",
base_provider = "",
best_provider = IterListProvider([
DDG,
Pizzagpt,
ReplicateHome,
Blackbox2,
Upstage,
Blackbox,
Free2GPT,
DeepInfraChat,
Airforce,
ChatGptEs,
Cloudflare,
Mhystical,
AmigoChat,
])
)
############
### Text ###
############
### OpenAI ###
# gpt-3.5
gpt_35_turbo = Model(
name = 'gpt-3.5-turbo',
base_provider = 'OpenAI',
best_provider = IterListProvider([Blackbox, ChatGptEs, PollinationsAI, DarkAI])
)
# gpt-4
gpt_4o = Model(
name = 'gpt-4o',
base_provider = 'OpenAI',
best_provider = IterListProvider([Blackbox, ChatGptEs, PollinationsAI, DarkAI, ChatGpt, AmigoChat, Airforce, Liaobots, OpenaiChat])
)
gpt_4o_mini = Model(
name = 'gpt-4o-mini',
base_provider = 'OpenAI',
best_provider = IterListProvider([DDG, Blackbox, ChatGptEs, Pizzagpt, ChatGpt, AmigoChat, Airforce, RubiksAI, MagickPen, Liaobots, OpenaiChat])
)
gpt_4_turbo = Model(
name = 'gpt-4-turbo',
base_provider = 'OpenAI',
best_provider = IterListProvider([Liaobots, Airforce])
)
gpt_4 = Model(
name = 'gpt-4',
base_provider = 'OpenAI',
best_provider = IterListProvider([DDG, Blackbox, PollinationsAI, Copilot, OpenaiChat, Liaobots, Airforce])
)
# o1
o1_preview = Model(
name = 'o1-preview',
base_provider = 'OpenAI',
best_provider = Liaobots
)
o1_mini = Model(
name = 'o1-mini',
base_provider = 'OpenAI',
best_provider = IterListProvider([Liaobots, Airforce])
)
### GigaChat ###
gigachat = Model(
name = 'GigaChat:latest',
base_provider = 'gigachat',
best_provider = GigaChat
)
### Meta ###
meta = Model(
name = "meta-ai",
base_provider = "Meta",
best_provider = MetaAI
)
# llama 2
llama_2_7b = Model(
name = "llama-2-7b",
base_provider = "Meta Llama",
best_provider = IterListProvider([Cloudflare, Airforce])
)
# llama 3
llama_3_8b = Model(
name = "llama-3-8b",
base_provider = "Meta Llama",
best_provider = Cloudflare
)
# llama 3.1
llama_3_1_8b = Model(
name = "llama-3.1-8b",
base_provider = "Meta Llama",
best_provider = IterListProvider([Blackbox, DeepInfraChat, Cloudflare, Airforce, PerplexityLabs])
)
llama_3_1_70b = Model(
name = "llama-3.1-70b",
base_provider = "Meta Llama",
best_provider = IterListProvider([DDG, DeepInfraChat, Blackbox, Blackbox2, TeachAnything, PollinationsAI, DarkAI, Airforce, RubiksAI, HuggingChat, HuggingFace, PerplexityLabs])
)
llama_3_1_405b = Model(
name = "llama-3.1-405b",
base_provider = "Meta Llama",
best_provider = IterListProvider([Blackbox, AmigoChat])
)
# llama 3.2
llama_3_2_1b = Model(
name = "llama-3.2-1b",
base_provider = "Meta Llama",
best_provider = Cloudflare
)
llama_3_2_11b = Model(
name = "llama-3.2-11b",
base_provider = "Meta Llama",
best_provider = IterListProvider([HuggingChat, HuggingFace])
)
llama_3_2_90b = Model(
name = "llama-3.2-90b",
base_provider = "Meta Llama",
best_provider = AmigoChat
)
# CodeLlama
codellama_34b = Model(
name = "codellama-34b",
base_provider = "Meta Llama",
best_provider = AmigoChat
)
### Mistral ###
mixtral_7b = Model(
name = "mixtral-7b",
base_provider = "Mistral",
best_provider = AmigoChat
)
mixtral_8x7b = Model(
name = "mixtral-8x7b",
base_provider = "Mistral",
best_provider = DDG
)
mistral_tiny = Model(
name = "mistral-tiny",
base_provider = "Mistral",
best_provider = AmigoChat
)
mistral_nemo = Model(
name = "mistral-nemo",
base_provider = "Mistral",
best_provider = IterListProvider([PollinationsAI, HuggingChat, AmigoChat, HuggingFace])
)
mistral_large = Model(
name = "mistral-large",
base_provider = "Mistral",
best_provider = PollinationsAI
)
### NousResearch ###
hermes_2_dpo = Model(
name = "hermes-2-dpo",
base_provider = "NousResearch",
best_provider = Airforce
)
hermes_2_pro = Model(
name = "hermes-2-pro",
base_provider = "NousResearch",
best_provider = Airforce
)
hermes_3 = Model(
name = "hermes-3",
base_provider = "NousResearch",
best_provider = IterListProvider([HuggingChat, HuggingFace])
)
mixtral_8x7b_dpo = Model(
name = "mixtral-8x7b-dpo",
base_provider = "NousResearch",
best_provider = IterListProvider([AmigoChat, Airforce])
)
### Microsoft ###
phi_2 = Model(
name = "phi-2",
base_provider = "Microsoft",
best_provider = Airforce
)
phi_3_5_mini = Model(
name = "phi-3.5-mini",
base_provider = "Microsoft",
best_provider = IterListProvider([HuggingChat, HuggingFace])
)
### Google DeepMind ###
# gemini
gemini_pro = Model(
name = 'gemini-pro',
base_provider = 'Google DeepMind',
best_provider = IterListProvider([Blackbox, AIChatFree, GeminiPro, Liaobots])
)
gemini_flash = Model(
name = 'gemini-flash',
base_provider = 'Google DeepMind',
best_provider = IterListProvider([Blackbox, AmigoChat, Liaobots])
)
gemini = Model(
name = 'gemini',
base_provider = 'Google DeepMind',
best_provider = Gemini
)
# gemma
gemma_2b = Model(
name = 'gemma-2b',
base_provider = 'Google',
best_provider = IterListProvider([ReplicateHome, AmigoChat])
)
### Anthropic ###
# claude 3
claude_3_opus = Model(
name = 'claude-3-opus',
base_provider = 'Anthropic',
best_provider = Liaobots
)
claude_3_sonnet = Model(
name = 'claude-3-sonnet',
base_provider = 'Anthropic',
best_provider = Liaobots
)
claude_3_haiku = Model(
name = 'claude-3-haiku',
base_provider = 'Anthropic',
best_provider = IterListProvider([DDG, Liaobots])
)
# claude 3.5
claude_3_5_sonnet = Model(
name = 'claude-3.5-sonnet',
base_provider = 'Anthropic',
best_provider = IterListProvider([Blackbox, PollinationsAI, AmigoChat, Liaobots])
)
claude_3_5_haiku = Model(
name = 'claude-3.5-haiku',
base_provider = 'Anthropic',
best_provider = AmigoChat
)
### Reka AI ###
reka_core = Model(
name = 'reka-core',
base_provider = 'Reka AI',
best_provider = Reka
)
### Blackbox AI ###
blackboxai = Model(
name = 'blackboxai',
base_provider = 'Blackbox AI',
best_provider = Blackbox
)
blackboxai_pro = Model(
name = 'blackboxai-pro',
base_provider = 'Blackbox AI',
best_provider = Blackbox
)
### CohereForAI ###
command_r_plus = Model(
name = 'command-r-plus',
base_provider = 'CohereForAI',
best_provider = IterListProvider([PollinationsAI, HuggingChat, AmigoChat])
)
### Qwen ###
# qwen 1_5
qwen_1_5_7b = Model(
name = 'qwen-1.5-7b',
base_provider = 'Qwen',
best_provider = Cloudflare
)
# qwen 2
qwen_2_72b = Model(
name = 'qwen-2-72b',
base_provider = 'Qwen',
best_provider = IterListProvider([DeepInfraChat, HuggingChat, HuggingFace])
)
# qwen 2.5
qwen_2_5_72b = Model(
name = 'qwen-2.5-72b',
base_provider = 'Qwen',
best_provider = IterListProvider([AmigoChat, HuggingChat, HuggingFace])
)
qwen_2_5_coder_32b = Model(
name = 'qwen-2.5-coder-32b',
base_provider = 'Qwen',
best_provider = IterListProvider([DeepInfraChat, PollinationsAI, HuggingChat, HuggingFace])
)
qwq_32b = Model(
name = 'qwq-32b',
base_provider = 'Qwen',
best_provider = IterListProvider([DeepInfraChat, HuggingChat, HuggingFace])
)
### Upstage ###
solar_mini = Model(
name = 'solar-mini',
base_provider = 'Upstage',
best_provider = Upstage
)
solar_pro = Model(
name = 'solar-pro',
base_provider = 'Upstage',
best_provider = Upstage
)
### Inflection ###
pi = Model(
name = 'pi',
base_provider = 'Inflection',
best_provider = Pi
)
### DeepSeek ###
deepseek_chat = Model(
name = 'deepseek-chat',
base_provider = 'DeepSeek',
best_provider = AmigoChat
)
deepseek_coder = Model(
name = 'deepseek-coder',
base_provider = 'DeepSeek',
best_provider = Airforce
)
### WizardLM ###
wizardlm_2_8x22b = Model(
name = 'wizardlm-2-8x22b',
base_provider = 'WizardLM',
best_provider = DeepInfraChat
)
### OpenChat ###
openchat_3_5 = Model(
name = 'openchat-3.5',
base_provider = 'OpenChat',
best_provider = Airforce
)
### x.ai ###
grok_2 = Model(
name = 'grok-2',
base_provider = 'x.ai',
best_provider = Liaobots
)
grok_2_mini = Model(
name = 'grok-2-mini',
base_provider = 'x.ai',
best_provider = Liaobots
)
grok_beta = Model(
name = 'grok-beta',
base_provider = 'x.ai',
best_provider = IterListProvider([AmigoChat, Liaobots])
)
### Perplexity AI ###
sonar_online = Model(
name = 'sonar-online',
base_provider = 'Perplexity AI',
best_provider = PerplexityLabs
)
sonar_chat = Model(
name = 'sonar-chat',
base_provider = 'Perplexity AI',
best_provider = PerplexityLabs
)
### Nvidia ###
nemotron_70b = Model(
name = 'nemotron-70b',
base_provider = 'Nvidia',
best_provider = IterListProvider([DeepInfraChat, HuggingChat, HuggingFace])
)
### Teknium ###
openhermes_2_5 = Model(
name = 'openhermes-2.5',
base_provider = 'Teknium',
best_provider = Airforce
)
### Liquid ###
lfm_40b = Model(
name = 'lfm-40b',
base_provider = 'Liquid',
best_provider = IterListProvider([Airforce, PerplexityLabs])
)
### DiscoResearch ###
german_7b = Model(
name = 'german-7b',
base_provider = 'DiscoResearch',
best_provider = Airforce
)
### HuggingFaceH4 ###
zephyr_7b = Model(
name = 'zephyr-7b',
base_provider = 'HuggingFaceH4',
best_provider = Airforce
)
### Inferless ###
neural_7b = Model(
name = 'neural-7b',
base_provider = 'inferless',
best_provider = Airforce
)
### Gryphe ###
mythomax_13b = Model(
name = 'mythomax-13b',
base_provider = 'Gryphe',
best_provider = AmigoChat
)
### databricks ###
dbrx_instruct = Model(
name = 'dbrx-instruct',
base_provider = 'databricks',
best_provider = AmigoChat
)
### anthracite-org ###
magnum_72b = Model(
name = 'magnum-72b',
base_provider = 'anthracite-org',
best_provider = AmigoChat
)
### ai21 ###
jamba_mini = Model(
name = 'jamba-mini',
base_provider = 'ai21',
best_provider = AmigoChat
)
### PollinationsAI ###
p1 = Model(
name = 'p1',
base_provider = 'PollinationsAI',
best_provider = PollinationsAI
)
### Uncensored AI ###
evil = Model(
name = 'evil',
base_provider = 'Evil Mode - Experimental',
best_provider = IterListProvider([PollinationsAI, Airforce])
)
#############
### Image ###
#############
### Stability AI ###
sdxl = ImageModel(
name = 'sdxl',
base_provider = 'Stability AI',
best_provider = IterListProvider([ReplicateHome, Airforce])
)
sd_3 = ImageModel(
name = 'sd-3',
base_provider = 'Stability AI',
best_provider = ReplicateHome
)
### Playground ###
playground_v2_5 = ImageModel(
name = 'playground-v2.5',
base_provider = 'Playground AI',
best_provider = ReplicateHome
)
### Flux AI ###
flux = ImageModel(
name = 'flux',
base_provider = 'Flux AI',
best_provider = IterListProvider([Blackbox, Blackbox2, PollinationsAI, Airforce])
)
flux_pro = ImageModel(
name = 'flux-pro',
base_provider = 'Flux AI',
best_provider = IterListProvider([PollinationsAI, Airforce])
)
flux_dev = ImageModel(
name = 'flux-dev',
base_provider = 'Flux AI',
best_provider = IterListProvider([Flux, AmigoChat, HuggingChat, HuggingFace])
)
flux_realism = ImageModel(
name = 'flux-realism',
base_provider = 'Flux AI',
best_provider = IterListProvider([PollinationsAI, Airforce, AmigoChat])
)
flux_cablyai = Model(
name = 'flux-cablyai',
base_provider = 'Flux AI',
best_provider = PollinationsAI
)
flux_anime = ImageModel(
name = 'flux-anime',
base_provider = 'Flux AI',
best_provider = IterListProvider([PollinationsAI, Airforce])
)
flux_3d = ImageModel(
name = 'flux-3d',
base_provider = 'Flux AI',
best_provider = IterListProvider([PollinationsAI, Airforce])
)
flux_disney = ImageModel(
name = 'flux-disney',
base_provider = 'Flux AI',
best_provider = Airforce
)
flux_pixel = ImageModel(
name = 'flux-pixel',
base_provider = 'Flux AI',
best_provider = Airforce
)
flux_4o = ImageModel(
name = 'flux-4o',
base_provider = 'Flux AI',
best_provider = Airforce
)
### OpenAI ###
dall_e_3 = ImageModel(
name = 'dall-e-3',
base_provider = 'OpenAI',
best_provider = IterListProvider([Airforce, CopilotAccount, OpenaiAccount, MicrosoftDesigner, BingCreateImages])
)
### Recraft ###
recraft_v3 = ImageModel(
name = 'recraft-v3',
base_provider = 'Recraft',
best_provider = AmigoChat
)
### Midjourney ###
midijourney = Model(
name = 'midijourney',
base_provider = 'Midjourney',
best_provider = PollinationsAI
)
### Other ###
any_dark = ImageModel(
name = 'any-dark',
base_provider = 'Other',
best_provider = IterListProvider([PollinationsAI, Airforce])
)
turbo = Model(
name = 'turbo',
base_provider = 'Other',
best_provider = PollinationsAI
)
unity = Model(
name = 'unity',
base_provider = 'Other',
best_provider = PollinationsAI
)
rtist = Model(
name = 'rtist',
base_provider = 'Other',
best_provider = PollinationsAI
)
class ModelUtils:
"""
Utility class for mapping string identifiers to Model instances.
Attributes:
convert (dict[str, Model]): Dictionary mapping model string identifiers to Model instances.
"""
convert: dict[str, Model] = {
############
### Text ###
############
### OpenAI ###
# gpt-3
'gpt-3': gpt_35_turbo,
# gpt-3.5
'gpt-3.5-turbo': gpt_35_turbo,
# gpt-4
'gpt-4o': gpt_4o,
'gpt-4o-mini': gpt_4o_mini,
'gpt-4': gpt_4,
'gpt-4-turbo': gpt_4_turbo,
# o1
'o1-preview': o1_preview,
'o1-mini': o1_mini,
### Meta ###
"meta-ai": meta,
# llama-2
'llama-2-7b': llama_2_7b,
# llama-3
'llama-3-8b': llama_3_8b,
# llama-3.1
'llama-3.1-8b': llama_3_1_8b,
'llama-3.1-70b': llama_3_1_70b,
'llama-3.1-405b': llama_3_1_405b,
# llama-3.2
'llama-3.2-1b': llama_3_2_1b,
'llama-3.2-11b': llama_3_2_11b,
'llama-3.2-90b': llama_3_2_90b,
# CodeLlama
'codellama-34b': codellama_34b,
### Mistral ###
'mixtral-7b': mixtral_7b,
'mixtral-8x7b': mixtral_8x7b,
'mistral-tiny': mistral_tiny,
'mistral-nemo': mistral_nemo,
'mistral-large': mistral_large,
### NousResearch ###
'mixtral-8x7b-dpo': mixtral_8x7b_dpo,
'hermes-2-dpo': hermes_2_dpo,
'hermes-2-pro': hermes_2_pro,
'hermes-3': hermes_3,
### Microsoft ###
'phi-2': phi_2,
'phi-3.5-mini': phi_3_5_mini,
### Google ###
# gemini
'gemini': gemini,
'gemini-pro': gemini_pro,
'gemini-flash': gemini_flash,
# gemma
'gemma-2b': gemma_2b,
### Anthropic ###
# claude 3
'claude-3-opus': claude_3_opus,
'claude-3-sonnet': claude_3_sonnet,
'claude-3-haiku': claude_3_haiku,
# claude 3.5
'claude-3.5-sonnet': claude_3_5_sonnet,
'claude-3.5-haiku': claude_3_5_haiku,
### Reka AI ###
'reka-core': reka_core,
### Blackbox AI ###
'blackboxai': blackboxai,
'blackboxai-pro': blackboxai_pro,
### CohereForAI ###
'command-r+': command_r_plus,
### GigaChat ###
'gigachat': gigachat,
### Qwen ###
# qwen 1_5
'qwen-1.5-7b': qwen_1_5_7b,
# qwen 2
'qwen-2-72b': qwen_2_72b,
# qwen 2.5
'qwen-2.5-72b': qwen_2_5_72b,
'qwen-2.5-coder-32b': qwen_2_5_coder_32b,
'qwq-32b': qwq_32b,
### Upstage ###
'solar-mini': solar_mini,
'solar-pro': solar_pro,
### Inflection ###
'pi': pi,
### WizardLM ###
'wizardlm-2-8x22b': wizardlm_2_8x22b,
### OpenChat ###
'openchat-3.5': openchat_3_5,
### x.ai ###
'grok-2': grok_2,
'grok-2-mini': grok_2_mini,
'grok-beta': grok_beta,
### Perplexity AI ###
'sonar-online': sonar_online,
'sonar-chat': sonar_chat,
### DeepSeek ###
'deepseek-chat': deepseek_chat,
'deepseek-coder': deepseek_coder,
### TheBloke ###
'german-7b': german_7b,
### Nvidia ###
'nemotron-70b': nemotron_70b,
### Teknium ###
'openhermes-2.5': openhermes_2_5,
### Liquid ###
'lfm-40b': lfm_40b,
### databricks ###
'dbrx-instruct': dbrx_instruct,
### anthracite-org ###
'magnum-72b': magnum_72b,
### anthracite-org ###
'jamba-mini': jamba_mini,
### HuggingFaceH4 ###
'zephyr-7b': zephyr_7b,
### Inferless ###
'neural-7b': neural_7b,
### Gryphe ###
'mythomax-13b': mythomax_13b,
### PollinationsAI ###
'p1': p1,
### Uncensored AI ###
'evil': evil,
#############
### Image ###
#############
### Stability AI ###
'sdxl': sdxl,
'sd-3': sd_3,
### Playground ###
'playground-v2.5': playground_v2_5,
### Flux AI ###
'flux': flux,
'flux-pro': flux_pro,
'flux-dev': flux_dev,
'flux-realism': flux_realism,
'flux-cablyai': flux_cablyai,
'flux-anime': flux_anime,
'flux-3d': flux_3d,
'flux-disney': flux_disney,
'flux-pixel': flux_pixel,
'flux-4o': flux_4o,
### OpenAI ###
'dall-e-3': dall_e_3,
### Recraft ###
'recraft-v3': recraft_v3,
### Midjourney ###
'midijourney': midijourney,
### Other ###
'any-dark': any_dark,
'turbo': turbo,
'unity': unity,
'rtist': rtist,
}
# Create a list of all working models
__models__ = {model.name: (model, providers) for model, providers in [
(model, [provider for provider in providers if provider.working])
for model, providers in [
(model, model.best_provider.providers
if isinstance(model.best_provider, IterListProvider)
else [model.best_provider]
if model.best_provider is not None
else [])
for model in ModelUtils.convert.values()]
] if providers}
# Update the ModelUtils.convert with the working models
ModelUtils.convert = {model.name: model for model, _ in __models__.values()}
_all_models = list(ModelUtils.convert.keys())
Reference in New Issue View Git Blame Copy Permalink