mirror of
https://github.com/tiennm99/litellm.git
synced 2026-07-20 18:20:33 +00:00
lint fix
This commit is contained in:
WilsonSunBritten
+249
-225
@@ -487,227 +487,247 @@ _openai_like_providers: List = [
|
||||
"watsonx",
|
||||
] # private helper. similar to openai but require some custom auth / endpoint handling, so can't use the openai sdk
|
||||
# well supported replicate llms
|
||||
replicate_models: set = set([
|
||||
# llama replicate supported LLMs
|
||||
"replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf",
|
||||
"a16z-infra/llama-2-13b-chat:2a7f981751ec7fdf87b5b91ad4db53683a98082e9ff7bfd12c8cd5ea85980a52",
|
||||
"meta/codellama-13b:1c914d844307b0588599b8393480a3ba917b660c7e9dfae681542b5325f228db",
|
||||
# Vicuna
|
||||
"replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b",
|
||||
"joehoover/instructblip-vicuna13b:c4c54e3c8c97cd50c2d2fec9be3b6065563ccf7d43787fb99f84151b867178fe",
|
||||
# Flan T-5
|
||||
"daanelson/flan-t5-large:ce962b3f6792a57074a601d3979db5839697add2e4e02696b3ced4c022d4767f",
|
||||
# Others
|
||||
"replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5",
|
||||
"replit/replit-code-v1-3b:b84f4c074b807211cd75e3e8b1589b6399052125b4c27106e43d47189e8415ad",
|
||||
])
|
||||
replicate_models: set = set(
|
||||
[
|
||||
# llama replicate supported LLMs
|
||||
"replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf",
|
||||
"a16z-infra/llama-2-13b-chat:2a7f981751ec7fdf87b5b91ad4db53683a98082e9ff7bfd12c8cd5ea85980a52",
|
||||
"meta/codellama-13b:1c914d844307b0588599b8393480a3ba917b660c7e9dfae681542b5325f228db",
|
||||
# Vicuna
|
||||
"replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b",
|
||||
"joehoover/instructblip-vicuna13b:c4c54e3c8c97cd50c2d2fec9be3b6065563ccf7d43787fb99f84151b867178fe",
|
||||
# Flan T-5
|
||||
"daanelson/flan-t5-large:ce962b3f6792a57074a601d3979db5839697add2e4e02696b3ced4c022d4767f",
|
||||
# Others
|
||||
"replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5",
|
||||
"replit/replit-code-v1-3b:b84f4c074b807211cd75e3e8b1589b6399052125b4c27106e43d47189e8415ad",
|
||||
]
|
||||
)
|
||||
|
||||
clarifai_models: set = set([
|
||||
"clarifai/meta.Llama-3.Llama-3-8B-Instruct",
|
||||
"clarifai/gcp.generate.gemma-1_1-7b-it",
|
||||
"clarifai/mistralai.completion.mixtral-8x22B",
|
||||
"clarifai/cohere.generate.command-r-plus",
|
||||
"clarifai/databricks.drbx.dbrx-instruct",
|
||||
"clarifai/mistralai.completion.mistral-large",
|
||||
"clarifai/mistralai.completion.mistral-medium",
|
||||
"clarifai/mistralai.completion.mistral-small",
|
||||
"clarifai/mistralai.completion.mixtral-8x7B-Instruct-v0_1",
|
||||
"clarifai/gcp.generate.gemma-2b-it",
|
||||
"clarifai/gcp.generate.gemma-7b-it",
|
||||
"clarifai/deci.decilm.deciLM-7B-instruct",
|
||||
"clarifai/mistralai.completion.mistral-7B-Instruct",
|
||||
"clarifai/gcp.generate.gemini-pro",
|
||||
"clarifai/anthropic.completion.claude-v1",
|
||||
"clarifai/anthropic.completion.claude-instant-1_2",
|
||||
"clarifai/anthropic.completion.claude-instant",
|
||||
"clarifai/anthropic.completion.claude-v2",
|
||||
"clarifai/anthropic.completion.claude-2_1",
|
||||
"clarifai/meta.Llama-2.codeLlama-70b-Python",
|
||||
"clarifai/meta.Llama-2.codeLlama-70b-Instruct",
|
||||
"clarifai/openai.completion.gpt-3_5-turbo-instruct",
|
||||
"clarifai/meta.Llama-2.llama2-7b-chat",
|
||||
"clarifai/meta.Llama-2.llama2-13b-chat",
|
||||
"clarifai/meta.Llama-2.llama2-70b-chat",
|
||||
"clarifai/openai.chat-completion.gpt-4-turbo",
|
||||
"clarifai/microsoft.text-generation.phi-2",
|
||||
"clarifai/meta.Llama-2.llama2-7b-chat-vllm",
|
||||
"clarifai/upstage.solar.solar-10_7b-instruct",
|
||||
"clarifai/openchat.openchat.openchat-3_5-1210",
|
||||
"clarifai/togethercomputer.stripedHyena.stripedHyena-Nous-7B",
|
||||
"clarifai/gcp.generate.text-bison",
|
||||
"clarifai/meta.Llama-2.llamaGuard-7b",
|
||||
"clarifai/fblgit.una-cybertron.una-cybertron-7b-v2",
|
||||
"clarifai/openai.chat-completion.GPT-4",
|
||||
"clarifai/openai.chat-completion.GPT-3_5-turbo",
|
||||
"clarifai/ai21.complete.Jurassic2-Grande",
|
||||
"clarifai/ai21.complete.Jurassic2-Grande-Instruct",
|
||||
"clarifai/ai21.complete.Jurassic2-Jumbo-Instruct",
|
||||
"clarifai/ai21.complete.Jurassic2-Jumbo",
|
||||
"clarifai/ai21.complete.Jurassic2-Large",
|
||||
"clarifai/cohere.generate.cohere-generate-command",
|
||||
"clarifai/wizardlm.generate.wizardCoder-Python-34B",
|
||||
"clarifai/wizardlm.generate.wizardLM-70B",
|
||||
"clarifai/tiiuae.falcon.falcon-40b-instruct",
|
||||
"clarifai/togethercomputer.RedPajama.RedPajama-INCITE-7B-Chat",
|
||||
"clarifai/gcp.generate.code-gecko",
|
||||
"clarifai/gcp.generate.code-bison",
|
||||
"clarifai/mistralai.completion.mistral-7B-OpenOrca",
|
||||
"clarifai/mistralai.completion.openHermes-2-mistral-7B",
|
||||
"clarifai/wizardlm.generate.wizardLM-13B",
|
||||
"clarifai/huggingface-research.zephyr.zephyr-7B-alpha",
|
||||
"clarifai/wizardlm.generate.wizardCoder-15B",
|
||||
"clarifai/microsoft.text-generation.phi-1_5",
|
||||
"clarifai/databricks.Dolly-v2.dolly-v2-12b",
|
||||
"clarifai/bigcode.code.StarCoder",
|
||||
"clarifai/salesforce.xgen.xgen-7b-8k-instruct",
|
||||
"clarifai/mosaicml.mpt.mpt-7b-instruct",
|
||||
"clarifai/anthropic.completion.claude-3-opus",
|
||||
"clarifai/anthropic.completion.claude-3-sonnet",
|
||||
"clarifai/gcp.generate.gemini-1_5-pro",
|
||||
"clarifai/gcp.generate.imagen-2",
|
||||
"clarifai/salesforce.blip.general-english-image-caption-blip-2",
|
||||
])
|
||||
clarifai_models: set = set(
|
||||
[
|
||||
"clarifai/meta.Llama-3.Llama-3-8B-Instruct",
|
||||
"clarifai/gcp.generate.gemma-1_1-7b-it",
|
||||
"clarifai/mistralai.completion.mixtral-8x22B",
|
||||
"clarifai/cohere.generate.command-r-plus",
|
||||
"clarifai/databricks.drbx.dbrx-instruct",
|
||||
"clarifai/mistralai.completion.mistral-large",
|
||||
"clarifai/mistralai.completion.mistral-medium",
|
||||
"clarifai/mistralai.completion.mistral-small",
|
||||
"clarifai/mistralai.completion.mixtral-8x7B-Instruct-v0_1",
|
||||
"clarifai/gcp.generate.gemma-2b-it",
|
||||
"clarifai/gcp.generate.gemma-7b-it",
|
||||
"clarifai/deci.decilm.deciLM-7B-instruct",
|
||||
"clarifai/mistralai.completion.mistral-7B-Instruct",
|
||||
"clarifai/gcp.generate.gemini-pro",
|
||||
"clarifai/anthropic.completion.claude-v1",
|
||||
"clarifai/anthropic.completion.claude-instant-1_2",
|
||||
"clarifai/anthropic.completion.claude-instant",
|
||||
"clarifai/anthropic.completion.claude-v2",
|
||||
"clarifai/anthropic.completion.claude-2_1",
|
||||
"clarifai/meta.Llama-2.codeLlama-70b-Python",
|
||||
"clarifai/meta.Llama-2.codeLlama-70b-Instruct",
|
||||
"clarifai/openai.completion.gpt-3_5-turbo-instruct",
|
||||
"clarifai/meta.Llama-2.llama2-7b-chat",
|
||||
"clarifai/meta.Llama-2.llama2-13b-chat",
|
||||
"clarifai/meta.Llama-2.llama2-70b-chat",
|
||||
"clarifai/openai.chat-completion.gpt-4-turbo",
|
||||
"clarifai/microsoft.text-generation.phi-2",
|
||||
"clarifai/meta.Llama-2.llama2-7b-chat-vllm",
|
||||
"clarifai/upstage.solar.solar-10_7b-instruct",
|
||||
"clarifai/openchat.openchat.openchat-3_5-1210",
|
||||
"clarifai/togethercomputer.stripedHyena.stripedHyena-Nous-7B",
|
||||
"clarifai/gcp.generate.text-bison",
|
||||
"clarifai/meta.Llama-2.llamaGuard-7b",
|
||||
"clarifai/fblgit.una-cybertron.una-cybertron-7b-v2",
|
||||
"clarifai/openai.chat-completion.GPT-4",
|
||||
"clarifai/openai.chat-completion.GPT-3_5-turbo",
|
||||
"clarifai/ai21.complete.Jurassic2-Grande",
|
||||
"clarifai/ai21.complete.Jurassic2-Grande-Instruct",
|
||||
"clarifai/ai21.complete.Jurassic2-Jumbo-Instruct",
|
||||
"clarifai/ai21.complete.Jurassic2-Jumbo",
|
||||
"clarifai/ai21.complete.Jurassic2-Large",
|
||||
"clarifai/cohere.generate.cohere-generate-command",
|
||||
"clarifai/wizardlm.generate.wizardCoder-Python-34B",
|
||||
"clarifai/wizardlm.generate.wizardLM-70B",
|
||||
"clarifai/tiiuae.falcon.falcon-40b-instruct",
|
||||
"clarifai/togethercomputer.RedPajama.RedPajama-INCITE-7B-Chat",
|
||||
"clarifai/gcp.generate.code-gecko",
|
||||
"clarifai/gcp.generate.code-bison",
|
||||
"clarifai/mistralai.completion.mistral-7B-OpenOrca",
|
||||
"clarifai/mistralai.completion.openHermes-2-mistral-7B",
|
||||
"clarifai/wizardlm.generate.wizardLM-13B",
|
||||
"clarifai/huggingface-research.zephyr.zephyr-7B-alpha",
|
||||
"clarifai/wizardlm.generate.wizardCoder-15B",
|
||||
"clarifai/microsoft.text-generation.phi-1_5",
|
||||
"clarifai/databricks.Dolly-v2.dolly-v2-12b",
|
||||
"clarifai/bigcode.code.StarCoder",
|
||||
"clarifai/salesforce.xgen.xgen-7b-8k-instruct",
|
||||
"clarifai/mosaicml.mpt.mpt-7b-instruct",
|
||||
"clarifai/anthropic.completion.claude-3-opus",
|
||||
"clarifai/anthropic.completion.claude-3-sonnet",
|
||||
"clarifai/gcp.generate.gemini-1_5-pro",
|
||||
"clarifai/gcp.generate.imagen-2",
|
||||
"clarifai/salesforce.blip.general-english-image-caption-blip-2",
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
huggingface_models: set = set([
|
||||
"meta-llama/Llama-2-7b-hf",
|
||||
"meta-llama/Llama-2-7b-chat-hf",
|
||||
"meta-llama/Llama-2-13b-hf",
|
||||
"meta-llama/Llama-2-13b-chat-hf",
|
||||
"meta-llama/Llama-2-70b-hf",
|
||||
"meta-llama/Llama-2-70b-chat-hf",
|
||||
"meta-llama/Llama-2-7b",
|
||||
"meta-llama/Llama-2-7b-chat",
|
||||
"meta-llama/Llama-2-13b",
|
||||
"meta-llama/Llama-2-13b-chat",
|
||||
"meta-llama/Llama-2-70b",
|
||||
"meta-llama/Llama-2-70b-chat",
|
||||
]) # these have been tested on extensively. But by default all text2text-generation and text-generation models are supported by liteLLM. - https://docs.litellm.ai/docs/providers
|
||||
empower_models = set([
|
||||
"empower/empower-functions",
|
||||
"empower/empower-functions-small",
|
||||
])
|
||||
huggingface_models: set = set(
|
||||
[
|
||||
"meta-llama/Llama-2-7b-hf",
|
||||
"meta-llama/Llama-2-7b-chat-hf",
|
||||
"meta-llama/Llama-2-13b-hf",
|
||||
"meta-llama/Llama-2-13b-chat-hf",
|
||||
"meta-llama/Llama-2-70b-hf",
|
||||
"meta-llama/Llama-2-70b-chat-hf",
|
||||
"meta-llama/Llama-2-7b",
|
||||
"meta-llama/Llama-2-7b-chat",
|
||||
"meta-llama/Llama-2-13b",
|
||||
"meta-llama/Llama-2-13b-chat",
|
||||
"meta-llama/Llama-2-70b",
|
||||
"meta-llama/Llama-2-70b-chat",
|
||||
]
|
||||
) # these have been tested on extensively. But by default all text2text-generation and text-generation models are supported by liteLLM. - https://docs.litellm.ai/docs/providers
|
||||
empower_models = set(
|
||||
[
|
||||
"empower/empower-functions",
|
||||
"empower/empower-functions-small",
|
||||
]
|
||||
)
|
||||
|
||||
together_ai_models: set = set([
|
||||
# llama llms - chat
|
||||
"togethercomputer/llama-2-70b-chat",
|
||||
# llama llms - language / instruct
|
||||
"togethercomputer/llama-2-70b",
|
||||
"togethercomputer/LLaMA-2-7B-32K",
|
||||
"togethercomputer/Llama-2-7B-32K-Instruct",
|
||||
"togethercomputer/llama-2-7b",
|
||||
# falcon llms
|
||||
"togethercomputer/falcon-40b-instruct",
|
||||
"togethercomputer/falcon-7b-instruct",
|
||||
# alpaca
|
||||
"togethercomputer/alpaca-7b",
|
||||
# chat llms
|
||||
"HuggingFaceH4/starchat-alpha",
|
||||
# code llms
|
||||
"togethercomputer/CodeLlama-34b",
|
||||
"togethercomputer/CodeLlama-34b-Instruct",
|
||||
"togethercomputer/CodeLlama-34b-Python",
|
||||
"defog/sqlcoder",
|
||||
"NumbersStation/nsql-llama-2-7B",
|
||||
"WizardLM/WizardCoder-15B-V1.0",
|
||||
"WizardLM/WizardCoder-Python-34B-V1.0",
|
||||
# language llms
|
||||
"NousResearch/Nous-Hermes-Llama2-13b",
|
||||
"Austism/chronos-hermes-13b",
|
||||
"upstage/SOLAR-0-70b-16bit",
|
||||
"WizardLM/WizardLM-70B-V1.0",
|
||||
])
|
||||
# supports all together ai models, just pass in the model id e.g. completion(model="together_computer/replit_code_3b",...)
|
||||
together_ai_models: set = set(
|
||||
[
|
||||
# llama llms - chat
|
||||
"togethercomputer/llama-2-70b-chat",
|
||||
# llama llms - language / instruct
|
||||
"togethercomputer/llama-2-70b",
|
||||
"togethercomputer/LLaMA-2-7B-32K",
|
||||
"togethercomputer/Llama-2-7B-32K-Instruct",
|
||||
"togethercomputer/llama-2-7b",
|
||||
# falcon llms
|
||||
"togethercomputer/falcon-40b-instruct",
|
||||
"togethercomputer/falcon-7b-instruct",
|
||||
# alpaca
|
||||
"togethercomputer/alpaca-7b",
|
||||
# chat llms
|
||||
"HuggingFaceH4/starchat-alpha",
|
||||
# code llms
|
||||
"togethercomputer/CodeLlama-34b",
|
||||
"togethercomputer/CodeLlama-34b-Instruct",
|
||||
"togethercomputer/CodeLlama-34b-Python",
|
||||
"defog/sqlcoder",
|
||||
"NumbersStation/nsql-llama-2-7B",
|
||||
"WizardLM/WizardCoder-15B-V1.0",
|
||||
"WizardLM/WizardCoder-Python-34B-V1.0",
|
||||
# language llms
|
||||
"NousResearch/Nous-Hermes-Llama2-13b",
|
||||
"Austism/chronos-hermes-13b",
|
||||
"upstage/SOLAR-0-70b-16bit",
|
||||
"WizardLM/WizardLM-70B-V1.0",
|
||||
]
|
||||
)
|
||||
# supports all together ai models, just pass in the model id e.g. completion(model="together_computer/replit_code_3b",...)
|
||||
|
||||
|
||||
baseten_models: set = set([
|
||||
"qvv0xeq",
|
||||
"q841o8w",
|
||||
"31dxrj3",
|
||||
]) # FALCON 7B # WizardLM # Mosaic ML
|
||||
baseten_models: set = set(
|
||||
[
|
||||
"qvv0xeq",
|
||||
"q841o8w",
|
||||
"31dxrj3",
|
||||
]
|
||||
) # FALCON 7B # WizardLM # Mosaic ML
|
||||
|
||||
featherless_ai_models: set = set([
|
||||
"featherless-ai/Qwerky-72B",
|
||||
"featherless-ai/Qwerky-QwQ-32B",
|
||||
"Qwen/Qwen2.5-72B-Instruct",
|
||||
"all-hands/openhands-lm-32b-v0.1",
|
||||
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"deepseek-ai/DeepSeek-V3-0324",
|
||||
"mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"mistralai/Mistral-Nemo-Instruct-2407",
|
||||
"ProdeusUnity/Stellar-Odyssey-12b-v0.0",
|
||||
])
|
||||
featherless_ai_models: set = set(
|
||||
[
|
||||
"featherless-ai/Qwerky-72B",
|
||||
"featherless-ai/Qwerky-QwQ-32B",
|
||||
"Qwen/Qwen2.5-72B-Instruct",
|
||||
"all-hands/openhands-lm-32b-v0.1",
|
||||
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"deepseek-ai/DeepSeek-V3-0324",
|
||||
"mistralai/Mistral-Small-24B-Instruct-2501",
|
||||
"mistralai/Mistral-Nemo-Instruct-2407",
|
||||
"ProdeusUnity/Stellar-Odyssey-12b-v0.0",
|
||||
]
|
||||
)
|
||||
|
||||
nebius_models: set = set([
|
||||
# deepseek models
|
||||
"deepseek-ai/DeepSeek-R1-0528",
|
||||
"deepseek-ai/DeepSeek-V3-0324",
|
||||
"deepseek-ai/DeepSeek-V3",
|
||||
"deepseek-ai/DeepSeek-R1",
|
||||
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
||||
# google models
|
||||
"google/gemma-2-2b-it",
|
||||
"google/gemma-2-9b-it-fast",
|
||||
# llama models
|
||||
"meta-llama/Llama-3.3-70B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct",
|
||||
"NousResearch/Hermes-3-Llama-405B",
|
||||
# microsoft models
|
||||
"microsoft/phi-4",
|
||||
# mistral models
|
||||
"mistralai/Mistral-Nemo-Instruct-2407",
|
||||
"mistralai/Devstral-Small-2505",
|
||||
# moonshot models
|
||||
"moonshotai/Kimi-K2-Instruct",
|
||||
# nvidia models
|
||||
"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",
|
||||
"nvidia/Llama-3_3-Nemotron-Super-49B-v1",
|
||||
# openai models
|
||||
"openai/gpt-oss-120b",
|
||||
"openai/gpt-oss-20b",
|
||||
# qwen models
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
"Qwen/Qwen3-235B-A22B-Instruct-2507",
|
||||
"Qwen/Qwen3-235B-A22B",
|
||||
"Qwen/Qwen3-30B-A3B",
|
||||
"Qwen/Qwen3-32B",
|
||||
"Qwen/Qwen3-14B",
|
||||
"Qwen/Qwen3-4B-fast",
|
||||
"Qwen/Qwen2.5-Coder-7B",
|
||||
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"Qwen/Qwen2.5-72B-Instruct",
|
||||
"Qwen/QwQ-32B",
|
||||
"Qwen/Qwen3-30B-A3B-Thinking-2507",
|
||||
"Qwen/Qwen3-30B-A3B-Instruct-2507",
|
||||
# zai models
|
||||
"zai-org/GLM-4.5",
|
||||
"zai-org/GLM-4.5-Air",
|
||||
# other models
|
||||
"aaditya/Llama3-OpenBioLLM-70B",
|
||||
"ProdeusUnity/Stellar-Odyssey-12b-v0.0",
|
||||
"all-hands/openhands-lm-32b-v0.1",
|
||||
])
|
||||
nebius_models: set = set(
|
||||
[
|
||||
# deepseek models
|
||||
"deepseek-ai/DeepSeek-R1-0528",
|
||||
"deepseek-ai/DeepSeek-V3-0324",
|
||||
"deepseek-ai/DeepSeek-V3",
|
||||
"deepseek-ai/DeepSeek-R1",
|
||||
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
||||
# google models
|
||||
"google/gemma-2-2b-it",
|
||||
"google/gemma-2-9b-it-fast",
|
||||
# llama models
|
||||
"meta-llama/Llama-3.3-70B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"meta-llama/Meta-Llama-3.1-405B-Instruct",
|
||||
"NousResearch/Hermes-3-Llama-405B",
|
||||
# microsoft models
|
||||
"microsoft/phi-4",
|
||||
# mistral models
|
||||
"mistralai/Mistral-Nemo-Instruct-2407",
|
||||
"mistralai/Devstral-Small-2505",
|
||||
# moonshot models
|
||||
"moonshotai/Kimi-K2-Instruct",
|
||||
# nvidia models
|
||||
"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",
|
||||
"nvidia/Llama-3_3-Nemotron-Super-49B-v1",
|
||||
# openai models
|
||||
"openai/gpt-oss-120b",
|
||||
"openai/gpt-oss-20b",
|
||||
# qwen models
|
||||
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
|
||||
"Qwen/Qwen3-235B-A22B-Instruct-2507",
|
||||
"Qwen/Qwen3-235B-A22B",
|
||||
"Qwen/Qwen3-30B-A3B",
|
||||
"Qwen/Qwen3-32B",
|
||||
"Qwen/Qwen3-14B",
|
||||
"Qwen/Qwen3-4B-fast",
|
||||
"Qwen/Qwen2.5-Coder-7B",
|
||||
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
||||
"Qwen/Qwen2.5-72B-Instruct",
|
||||
"Qwen/QwQ-32B",
|
||||
"Qwen/Qwen3-30B-A3B-Thinking-2507",
|
||||
"Qwen/Qwen3-30B-A3B-Instruct-2507",
|
||||
# zai models
|
||||
"zai-org/GLM-4.5",
|
||||
"zai-org/GLM-4.5-Air",
|
||||
# other models
|
||||
"aaditya/Llama3-OpenBioLLM-70B",
|
||||
"ProdeusUnity/Stellar-Odyssey-12b-v0.0",
|
||||
"all-hands/openhands-lm-32b-v0.1",
|
||||
]
|
||||
)
|
||||
|
||||
dashscope_models: set = set([
|
||||
"qwen-turbo",
|
||||
"qwen-plus",
|
||||
"qwen-max",
|
||||
"qwen-turbo-latest",
|
||||
"qwen-plus-latest",
|
||||
"qwen-max-latest",
|
||||
"qwq-32b",
|
||||
"qwen3-235b-a22b",
|
||||
"qwen3-32b",
|
||||
"qwen3-30b-a3b",
|
||||
])
|
||||
dashscope_models: set = set(
|
||||
[
|
||||
"qwen-turbo",
|
||||
"qwen-plus",
|
||||
"qwen-max",
|
||||
"qwen-turbo-latest",
|
||||
"qwen-plus-latest",
|
||||
"qwen-max-latest",
|
||||
"qwq-32b",
|
||||
"qwen3-235b-a22b",
|
||||
"qwen3-32b",
|
||||
"qwen3-30b-a3b",
|
||||
]
|
||||
)
|
||||
|
||||
nebius_embedding_models: set = set([
|
||||
"BAAI/bge-en-icl",
|
||||
"BAAI/bge-multilingual-gemma2",
|
||||
"intfloat/e5-mistral-7b-instruct",
|
||||
])
|
||||
nebius_embedding_models: set = set(
|
||||
[
|
||||
"BAAI/bge-en-icl",
|
||||
"BAAI/bge-multilingual-gemma2",
|
||||
"intfloat/e5-mistral-7b-instruct",
|
||||
]
|
||||
)
|
||||
|
||||
BEDROCK_INVOKE_PROVIDERS_LITERAL = Literal[
|
||||
"cohere",
|
||||
@@ -722,20 +742,24 @@ BEDROCK_INVOKE_PROVIDERS_LITERAL = Literal[
|
||||
]
|
||||
|
||||
open_ai_embedding_models: set = set(["text-embedding-ada-002"])
|
||||
cohere_embedding_models: set = set([
|
||||
"embed-v4.0",
|
||||
"embed-english-v3.0",
|
||||
"embed-english-light-v3.0",
|
||||
"embed-multilingual-v3.0",
|
||||
"embed-english-v2.0",
|
||||
"embed-english-light-v2.0",
|
||||
"embed-multilingual-v2.0",
|
||||
])
|
||||
bedrock_embedding_models: set = set([
|
||||
"amazon.titan-embed-text-v1",
|
||||
"cohere.embed-english-v3",
|
||||
"cohere.embed-multilingual-v3",
|
||||
])
|
||||
cohere_embedding_models: set = set(
|
||||
[
|
||||
"embed-v4.0",
|
||||
"embed-english-v3.0",
|
||||
"embed-english-light-v3.0",
|
||||
"embed-multilingual-v3.0",
|
||||
"embed-english-v2.0",
|
||||
"embed-english-light-v2.0",
|
||||
"embed-multilingual-v2.0",
|
||||
]
|
||||
)
|
||||
bedrock_embedding_models: set = set(
|
||||
[
|
||||
"amazon.titan-embed-text-v1",
|
||||
"cohere.embed-english-v3",
|
||||
"cohere.embed-multilingual-v3",
|
||||
]
|
||||
)
|
||||
|
||||
known_tokenizer_config = {
|
||||
"mistralai/Mistral-7B-Instruct-v0.1": {
|
||||
|
||||
Reference in New Issue
Block a user