librechat / librechat.yaml
andrewm-dta's picture
Update librechat.yaml
df7951e unverified
raw
history blame
30.2 kB
#updated
version: 1.1.4
cache: true
registration:
socialLogins: ["google"]
endpoints:
custom:
# Anyscale
# - name: "Anyscale"
# apiKey: "${ANYSCALE_API_KEY}"
# baseURL: "https://api.endpoints.anyscale.com/v1"
# models:
# default: [
# "meta-llama/Llama-2-7b-chat-hf",
# "meta-llama/Llama-2-13b-chat-hf",
# "meta-llama/Llama-2-70b-chat-hf",
# "codellama/CodeLlama-34b-Instruct-hf",
# "codellama/CodeLlama-70b-Instruct-hf",
# "mistralai/Mistral-7B-Instruct-v0.1",
# "mistralai/Mixtral-8x7B-Instruct-v0.1",
# "mlabonne/NeuralHermes-2.5-Mistral-7B",
# "Open-Orca/Mistral-7B-OpenOrca",
# "HuggingFaceH4/zephyr-7b-beta",
# "google/gemma-7b-it"
# ]
# fetch: false
# titleConvo: true
# titleModel: "meta-llama/Llama-2-7b-chat-hf"
# summarize: false
# summaryModel: "meta-llama/Llama-2-7b-chat-hf"
# forcePrompt: false
# modelDisplayLabel: "Anyscale"
# APIpie
# # - name: "APIpie"
# apiKey: "${APIPIE_API_KEY}"
# baseURL: "https://apipie.ai/v1/"
# models:
# default: [
# "BioM-ELECTRA-Large-SQuAD2",
# "Bio_ClinicalBERT",
# "Bio_Discharge_Summary_BERT",
# "BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
# "GPT-JT-Moderation-6B",
# "German-MedBERT",
# "LLaMA-2-7B-32K",
# "Llama-2-13b-chat-hf",
# "Llama-2-13b-hf",
# "Llama-2-70b-chat-hf",
# "Llama-2-70b-hf",
# "Llama-2-7B-32K-Instruct",
# "Llama-2-7b-chat-hf",
# "Llama-2-7b-hf",
# "Meta-Llama-3-70B-Instruct",
# "Meta-Llama-3-8B-Instruct",
# "Mistral-7B-Instruct-v0.1",
# "Mistral-7B-Instruct-v0.2",
# "Mistral-7B-OpenOrca",
# "Mixtral-8x22B-Instruct-v0.1",
# "Mixtral-8x22B-v0.1",
# "Mixtral-8x7B-Instruct-v0.1",
# "Mixtral-8x7B-v0.1",
# "MythoMax-L2-13b",
# "NexusRaven-V2-13B",
# "Nous-Hermes-2-Mixtral-8x7B-DPO",
# "Nous-Hermes-2-Mixtral-8x7B-SFT",
# "Nous-Hermes-Llama2-13b",
# "Nous-Hermes-llama-2-7b",
# "ReMM-SLERP-L2-13B",
# "RedPajama-INCITE-7B-Base",
# "RedPajama-INCITE-7B-Chat",
# "RedPajama-INCITE-7B-Instruct",
# "RedPajama-INCITE-Base-3B-v1",
# "RedPajama-INCITE-Chat-3B-v1",
# "RedPajama-INCITE-Instruct-3B-v1",
# "SecBERT",
# "TinyLlama-1.1B-Chat-v1.0",
# "Toppy-M-7B",
# "WizardLM-2-7B",
# "WizardLM-2-8x22B",
# "Yi-34B-Chat",
# "airoboros-70b",
# "airoboros-l2-70b",
# "albert-base-chinese-cluecorpussmall",
# "albert-base-v1",
# "albert-base-v2",
# "alpaca-7b",
# "babbage-002",
# "bert-base",
# "bert-base-arabertv02",
# "bert-base-cased",
# "bert-base-chinese",
# "bert-base-german-cased",
# "bert-base-multilingual-cased",
# "bert-base-multilingual-uncased",
# "bert-base-portuguese-cased",
# "bert-base-swedish-cased",
# "bert-base-uncased",
# "bert-base-uncased-squad-v1",
# "bert-large-cased",
# "bert-large-portuguese-cased",
# "bert-large-uncased",
# "bert-large-uncased-whole-word-masking-finetuned-squad",
# "bert-large-uncased-whole-word-masking-squad2",
# "biobert-base-cased-v1.2",
# "chat-bison",
# "chinese-bert-wwm-ext",
# "chinese-roberta-wwm-ext",
# "chronos-hermes-13b",
# "chronos-hermes-13b-v2",
# "cinematika-7b",
# "claude-1",
# "claude-1.2",
# "claude-2",
# "claude-2.0",
# "claude-2.1",
# "claude-3-haiku",
# "claude-3-opus",
# "claude-3-sonnet",
# "claude-instant-1",
# "claude-instant-1.0",
# "claude-instant-1.1",
# "claude-instant-1.2",
# "command",
# "command-light",
# "command-light-nightly",
# "command-light-text-v14",
# "command-nightly",
# "command-r",
# "command-r-plus",
# "command-r-plus-v1",
# "command-r-v1",
# "command-text-v14",
# "davinci-002",
# "dbrx-instruct",
# "deberta-base",
# "deberta-v2-xlarge",
# "deberta-v3-base",
# "deepseek-chat",
# "distilbert-base-cased-distilled-squad",
# "distilbert-base-multilingual-cased",
# "distilbert-base-uncased",
# "distilbert-base-uncased-distilled-squad",
# "dolphin-2.5-mixtral-8x7b",
# "dolphin-2.6-mixtral-8x7b",
# "dolphin-mixtral-8x7b",
# "eagle-7b",
# "fimbulvetr-11b-v2",
# "firellava-13b",
# "gemini-flash-1.5",
# "gemini-pro",
# "gemini-pro-1.5",
# "gemini-pro-vision",
# "gemma-1.1-7b-it",
# "gemma-7b-it",
# "goliath-120b",
# "gpt-3.5-turbo",
# "gpt-3.5-turbo-0125",
# "gpt-3.5-turbo-0301",
# "gpt-3.5-turbo-0613",
# "gpt-3.5-turbo-1106",
# "gpt-3.5-turbo-16k",
# "gpt-3.5-turbo-16k-0613",
# "gpt-3.5-turbo-instruct",
# "gpt-3.5-turbo-instruct-0914",
# "gpt-4",
# "gpt-4-0125-preview",
# "gpt-4-0314",
# "gpt-4-0613",
# "gpt-4-1106-preview",
# "gpt-4-1106-vision-preview",
# "gpt-4-32k",
# "gpt-4-32k-0314",
# "gpt-4-turbo",
# "gpt-4-turbo-2024-04-09",
# "gpt-4-turbo-preview",
# "gpt-4-vision-preview",
# "gpt-4o",
# "gpt-4o-2024-05-13",
# "gpt-4o-test-shared",
# "hermes-2-pro-llama-3-8b",
# "j2-grande-instruct",
# "j2-jumbo-instruct",
# "j2-mid",
# "j2-mid-v1",
# "j2-ultra",
# "j2-ultra-v1",
# "koelectra-small-v2-distilled-korquad-384",
# "large-latest",
# "legal-bert-base-uncased",
# "legal-bert-small-uncased",
# "llama-2-13b-chat",
# "llama-2-70b-chat",
# "llama-3-70b",
# "llama-3-70b-instruct",
# "llama-3-8b",
# "llama-3-8b-instruct",
# "llama-3-lumimaid-70b",
# "llama-3-lumimaid-8b",
# "llama-3-sonar-large-32k-chat",
# "llama-3-sonar-large-32k-online",
# "llama-3-sonar-small-32k-chat",
# "llama-3-sonar-small-32k-online",
# "llama-guard-2-8b",
# "llama2-13b-chat-v1",
# "llama2-70b-chat-v1",
# "llama3-70b-instruct-v1",
# "llama3-8b-instruct-v1",
# "llava-1.5-7b-hf",
# "llava-13b",
# "llava-yi-34b",
# "lzlv-70b-fp16-hf",
# "lzlv_70b_fp16_hf",
# "medium",
# "midnight-rose-70b",
# "minilm-uncased-squad2",
# "mistral-7b-instruct",
# "mistral-7b-instruct-v0",
# "mistral-7b-instruct-v0.1",
# "mistral-7b-instruct-v0.2",
# "mistral-7b-instruct-v0.3",
# "mistral-large",
# "mistral-medium",
# "mistral-small",
# "mistral-small-2402-v1",
# "mistral-tiny",
# "mixtral-8x22b",
# "mixtral-8x22b-instruct",
# "mixtral-8x22b-instruct-preview",
# "mixtral-8x7b",
# "mixtral-8x7b-instruct",
# "mixtral-8x7b-instruct-v0",
# "mythalion-13b",
# "mythomax-l2-13b",
# "mythomist-7b",
# "neural-chat-7b",
# "noromaid-20b",
# "noromaid-mixtral-8x7b-instruct",
# "nous-capybara-34b",
# "nous-capybara-7b",
# "nous-hermes-2-mistral-7b-dpo",
# "nous-hermes-2-mixtral-8x7b-dpo",
# "nous-hermes-2-mixtral-8x7b-sft",
# "nous-hermes-2-vision-7b",
# "nous-hermes-llama2-13b",
# "nous-hermes-yi-34b",
# "olmo-7b-instruct",
# "olympus-premier-v1",
# "openchat-3.5-1210",
# "openchat-7b",
# "openchat_3.5",
# "openhermes-2-mistral-7b",
# "openhermes-2.5-mistral-7b",
# "palm-2-chat-bison",
# "palm-2-chat-bison-32k",
# "phi-2",
# "phi-3-medium-128k-instruct",
# "phi-3-mini-128k-instruct",
# "pplx-70b-chat",
# "pplx-70b-online",
# "pplx-7b-chat",
# "pplx-7b-online",
# "prot_bert",
# "prot_bert_bfd",
# "psyfighter-13b-2",
# "qwen-110b-chat",
# "qwen-14b-chat",
# "qwen-32b-chat",
# "qwen-4b-chat",
# "qwen-72b-chat",
# "qwen-7b-chat",
# "remm-slerp-l2-13b",
# "roberta-base-squad2",
# "roberta-base-squad2-covid",
# "roberta-large-squad2",
# "small",
# "snowflake-arctic-instruct",
# "soliloquy-l3",
# "sonar-medium-chat",
# "sonar-medium-online",
# "sonar-small-chat",
# "sonar-small-online",
# "splade-cocondenser-ensembledistil",
# "stripedhyena-hessian-7b",
# "stripedhyena-nous-7b",
# "synthia-70b",
# "text-babbage-002",
# "text-bison",
# "text-davinci-002",
# "tiny",
# "tinyroberta-squad2",
# "titan-text-express-v1",
# "titan-text-lite-v1",
# "titan-text-premier-v1",
# "titan-tg1-large",
# "toppy-m-7b",
# "vicuna-13b-v1.5",
# "vicuna-7b-v1.5",
# "weaver",
# "wizardlm-2-7b",
# "wizardlm-2-8x22b",
# "xwin-lm-70b",
# "yi-34b",
# "yi-34b-chat",
# "yi-6b",
# "zephyr-7b-beta",
# "zephyr-orpo-141b-A35b-v0.1"
# ]
# fetch: false
# titleConvo: true
# titleModel: "claude-3-haiku"
# summarize: false
# summaryModel: "claude-3-haiku"
# dropParams: ["stream"]
# modelDisplayLabel: "APIpie"
# iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/APIpie.png"
#cohere
# - name: "cohere"
# apiKey: "${COHERE_API_KEY}"
# baseURL: "https://api.cohere.ai/v1"
# models:
# default: ["command-r","command-r-plus","command-light","command-light-nightly","command","command-nightly"]
# fetch: false
# modelDisplayLabel: "cohere"
# titleModel: "command"
# dropParams: ["stop", "user", "frequency_penalty", "presence_penalty", "temperature", "top_p"]
# DEEPNIGHT
# - name: "DEEPNIGHT"
# apiKey: "sk-free1234"
# baseURL: "https://aiforcause.deepnight.tech/openai/"
# models:
# default: [
# "gpt-35-turbo",
# "gpt-35-turbo-16k",
# "gpt-4-turbo"
# ]
# fetch: false
# titleConvo: true
# titleModel: "gpt-35-turbo"
# summarize: false
# summaryModel: "gpt-35-turbo"
# forcePrompt: false
# modelDisplayLabel: "DEEPNIGHT"
# addParams:
# stream: True
# iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/DEEPNIGHT.png"
# Fireworks.ai
# - name: "Fireworks"
# apiKey: "${FIREWORKS_API_KEY}"
# baseURL: "https://api.fireworks.ai/inference/v1"
# models:
# default: [
# "accounts/fireworks/models/devashisht-test-v2",
# "accounts/fireworks/models/dt-fc-rc-v1",
# "accounts/fireworks/models/firefunction-v1",
# "accounts/fireworks/models/firellava-13b",
# "accounts/devashisht-72fdad/models/function-calling-v11",
# "accounts/fireworks/models/fw-function-call-34b-v0",
# "accounts/stability/models/japanese-stablelm-instruct-beta-70b",
# "accounts/stability/models/japanese-stablelm-instruct-gamma-7b",
# "accounts/fireworks/models/japanese-stable-vlm",
# "accounts/fireworks/models/llama-v2-13b-chat",
# "accounts/fireworks/models/llama-v2-13b-code-instruct",
# "accounts/fireworks/models/llama-v2-34b-code-instruct",
# "accounts/fireworks/models/llama-v2-70b-chat",
# "accounts/fireworks/models/llama-v2-70b-code-instruct",
# "accounts/fireworks/models/llama-v2-7b-chat",
# "accounts/fireworks/models/llava-v15-13b-fireworks",
# "accounts/fireworks/models/mistral-7b-instruct-4k",
# "accounts/dev-e24710/models/mistral-spellbound-format",
# "accounts/fireworks/models/mixtral-8x7b-instruct",
# "accounts/fireworks/models/mixtral-8x7b-instruct-hf",
# "accounts/fireworks/models/new-mixtral-chat",
# "accounts/fireworks/models/qwen-14b-chat",
# "accounts/fireworks/models/qwen-1-8b-chat",
# "accounts/fireworks/models/qwen-72b-chat",
# "accounts/stability/models/stablelm-zephyr-3b",
# "accounts/fireworks/models/yi-34b-200k-capybara",
# ]
# fetch: false
# titleConvo: true
# titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
# summarize: false
# summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
# forcePrompt: false
# modelDisplayLabel: "Fireworks"
# dropParams: ["user"]
# groq
# - name: "groq"
# apiKey: "${GROQ_API_KEY}"
# baseURL: "https://api.groq.com/openai/v1/"
# models:
# default: [
# "llama2-70b-4096",
# "llama3-70b-8192",
# "llama3-8b-8192",
# "mixtral-8x7b-32768",
# "gemma-7b-it",
# ]
# fetch: false
# titleConvo: true
# titleModel: "mixtral-8x7b-32768"
# modelDisplayLabel: "groq"
# Mistral AI API
# - name: "Mistral"
# apiKey: "${MISTRAL_API_KEY}"
# baseURL: "https://api.mistral.ai/v1"
# models:
# default: [
# "mistral-tiny",
# "mistral-small",
# "mistral-medium",
# "mistral-large-latest"
# ]
# fetch: false
# titleConvo: true
# titleMethod: "completion"
# titleModel: "mistral-tiny"
# summarize: false
# summaryModel: "mistral-tiny"
# forcePrompt: false
# modelDisplayLabel: "Mistral"
# dropParams: ["stop", "user", "frequency_penalty", "presence_penalty"]
# OpenRouter.ai
- name: "OpenRouter"
apiKey: "${OPENROUTER_KEY}"
baseURL: "https://openrouter.ai/api/v1"
models:
"default": [
"openrouter/auto",
"---FREE---",
"google/gemma-7b-it:free",
"gryphe/mythomist-7b:free",
"huggingfaceh4/zephyr-7b-beta:free",
"meta-llama/llama-3-8b-instruct:free",
"microsoft/phi-3-medium-128k-instruct:free",
"microsoft/phi-3-mini-128k-instruct:free",
"mistralai/mistral-7b-instruct:free",
"nousresearch/nous-capybara-7b:free",
"openchat/openchat-7b:free",
"openrouter/cinematika-7b:free",
"undi95/toppy-m-7b:free",
"---NITRO---",
"google/gemma-7b-it:nitro",
"gryphe/mythomax-l2-13b:nitro",
"meta-llama/llama-2-70b-chat:nitro",
"meta-llama/llama-3-70b-instruct:nitro",
"meta-llama/llama-3-8b-instruct:nitro",
"mistralai/mistral-7b-instruct:nitro",
"mistralai/mixtral-8x7b-instruct:nitro",
"undi95/toppy-m-7b:nitro",
"---BETA---",
"anthropic/claude-2.0:beta",
"anthropic/claude-2.1:beta",
"anthropic/claude-2:beta",
"anthropic/claude-3-haiku:beta",
"anthropic/claude-3-opus:beta",
"anthropic/claude-3-sonnet:beta",
"anthropic/claude-instant-1:beta",
"---EXTENDED---",
"gryphe/mythomax-l2-13b:extended",
"meta-llama/llama-3-8b-instruct:extended",
"neversleep/llama-3-lumimaid-8b:extended",
"undi95/remm-slerp-l2-13b:extended",
"---01-AI---",
"01-ai/yi-34b",
"01-ai/yi-34b-chat",
"01-ai/yi-6b",
"---ANTHROPIC---",
"anthropic/claude-1",
"anthropic/claude-1.2",
"anthropic/claude-2",
"anthropic/claude-2.0",
"anthropic/claude-2.1",
"anthropic/claude-3-haiku",
"anthropic/claude-3-opus",
"anthropic/claude-3-sonnet",
"anthropic/claude-instant-1",
"anthropic/claude-instant-1.0",
"anthropic/claude-instant-1.1",
"---COHERE---",
"cohere/command",
"cohere/command-r",
"cohere/command-r-plus",
"---GOOGLE---",
"google/gemini-flash-1.5",
"google/gemini-pro",
"google/gemini-pro-1.5",
"google/gemini-pro-vision",
"google/gemma-7b-it",
"google/palm-2-chat-bison",
"google/palm-2-chat-bison-32k",
"google/palm-2-codechat-bison",
"google/palm-2-codechat-bison-32k",
"---META-LLAMA---",
"meta-llama/codellama-34b-instruct",
"meta-llama/llama-2-13b-chat",
"meta-llama/llama-2-70b-chat",
"meta-llama/llama-3-70b",
"meta-llama/llama-3-70b-instruct",
"meta-llama/llama-3-8b",
"meta-llama/llama-3-8b-instruct",
"meta-llama/llama-guard-2-8b",
"---MICROSOFT---",
"microsoft/phi-3-medium-128k-instruct",
"microsoft/phi-3-mini-128k-instruct",
"microsoft/wizardlm-2-7b",
"microsoft/wizardlm-2-8x22b",
"---MISTRALAI---",
"mistralai/mistral-7b-instruct",
"mistralai/mistral-7b-instruct-v0.1",
"mistralai/mistral-7b-instruct-v0.2",
"mistralai/mistral-7b-instruct-v0.3",
"mistralai/mistral-large",
"mistralai/mistral-medium",
"mistralai/mistral-small",
"mistralai/mistral-tiny",
"mistralai/mixtral-8x22b",
"mistralai/mixtral-8x22b-instruct",
"mistralai/mixtral-8x7b",
"mistralai/mixtral-8x7b-instruct",
"---NEVERSLEEP---",
"neversleep/llama-3-lumimaid-70b",
"neversleep/llama-3-lumimaid-8b",
"neversleep/noromaid-20b",
"neversleep/noromaid-mixtral-8x7b-instruct",
"---NOUSRESEARCH---",
"nousresearch/hermes-2-pro-llama-3-8b",
"nousresearch/nous-capybara-34b",
"nousresearch/nous-capybara-7b",
"nousresearch/nous-hermes-2-mistral-7b-dpo",
"nousresearch/nous-hermes-2-mixtral-8x7b-dpo",
"nousresearch/nous-hermes-2-mixtral-8x7b-sft",
"nousresearch/nous-hermes-2-vision-7b",
"nousresearch/nous-hermes-llama2-13b",
"nousresearch/nous-hermes-yi-34b",
"---OPENAI---",
"openai/gpt-3.5-turbo",
"openai/gpt-3.5-turbo-0125",
"openai/gpt-3.5-turbo-0301",
"openai/gpt-3.5-turbo-0613",
"openai/gpt-3.5-turbo-1106",
"openai/gpt-3.5-turbo-16k",
"openai/gpt-3.5-turbo-instruct",
"openai/gpt-4",
"openai/gpt-4-0314",
"openai/gpt-4-1106-preview",
"openai/gpt-4-32k",
"openai/gpt-4-32k-0314",
"openai/gpt-4-turbo",
"openai/gpt-4-turbo-preview",
"openai/gpt-4-vision-preview",
"openai/gpt-4o",
"openai/gpt-4o-2024-05-13",
"---PERPLEXITY---",
"perplexity/llama-3-sonar-large-32k-chat",
"perplexity/llama-3-sonar-large-32k-online",
"perplexity/llama-3-sonar-small-32k-chat",
"perplexity/llama-3-sonar-small-32k-online",
"---QWEN---",
"qwen/qwen-110b-chat",
"qwen/qwen-14b-chat",
"qwen/qwen-32b-chat",
"qwen/qwen-4b-chat",
"qwen/qwen-72b-chat",
"qwen/qwen-7b-chat",
"---OTHERS---",
"allenai/olmo-7b-instruct",
"alpindale/goliath-120b",
"austism/chronos-hermes-13b",
"codellama/codellama-70b-instruct",
"cognitivecomputations/dolphin-mixtral-8x7b",
"databricks/dbrx-instruct",
"deepseek/deepseek-chat",
"deepseek/deepseek-coder",
"fireworks/firellava-13b",
"gryphe/mythomax-l2-13b",
"gryphe/mythomist-7b",
"huggingfaceh4/zephyr-7b-beta",
"intel/neural-chat-7b",
"jebcarter/psyfighter-13b",
"jondurbin/airoboros-l2-70b",
"jondurbin/bagel-34b",
"koboldai/psyfighter-13b-2",
"liuhaotian/llava-13b",
"liuhaotian/llava-yi-34b",
"lizpreciatior/lzlv-70b-fp16-hf",
"lynn/soliloquy-l3",
"mancer/weaver",
"open-orca/mistral-7b-openorca",
"openchat/openchat-7b",
"openrouter/cinematika-7b",
"phind/phind-codellama-34b",
"pygmalionai/mythalion-13b",
"recursal/eagle-7b",
"recursal/rwkv-5-3b-ai-town",
"rwkv/rwkv-5-world-3b",
"sao10k/fimbulvetr-11b-v2",
"snowflake/snowflake-arctic-instruct",
"sophosympatheia/midnight-rose-70b",
"teknium/openhermes-2-mistral-7b",
"teknium/openhermes-2.5-mistral-7b",
"togethercomputer/stripedhyena-hessian-7b",
"togethercomputer/stripedhyena-nous-7b",
"undi95/remm-slerp-l2-13b",
"undi95/toppy-m-7b",
"xwin-lm/xwin-lm-70b"
]
fetch: false
dropParams: ["stop"]
titleConvo: true
titleModel: "gpt-3.5-turbo"
summarize: false
summaryModel: "gpt-3.5-turbo"
forcePrompt: false
modelDisplayLabel: "OpenRouter"
# # OpenRouter.ai - Perplexity
# - name: "OpenRouter-Perplexity"
# apiKey: "${OPENROUTER_KEY}"
# baseURL: "https://openrouter.ai/api/v1"
# models:
# "default": [
# "perplexity/pplx-7b-chat",
# "perplexity/pplx-70b-chat",
# "perplexity/pplx-7b-online",
# "perplexity/pplx-70b-online",
# "perplexity/sonar-medium-online",
# ]
# fetch: false
# titleConvo: true
# titleModel: "perplexity/pplx-7b-chat"
# summarize: false
# summaryModel: "perplexity/pplx-7b-chat"
# forcePrompt: false
# dropParams: ["stop"]
# modelDisplayLabel: "Perplexity"
# iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/perplexityai.png"
- name: "Perplexity"
apiKey: "${PERPLEXITY_API_KEY}"
baseURL: "https://api.perplexity.ai/"
models:
default: [
"mistral-7b-instruct",
"sonar-small-chat",
"sonar-small-online",
"sonar-medium-chat",
"sonar-medium-online"
]
fetch: false # fetching list of models is not supported
titleConvo: true
titleModel: "sonar-medium-chat"
summarize: false
summaryModel: "sonar-medium-chat"
forcePrompt: false
dropParams: ["stop", "frequency_penalty"]
modelDisplayLabel: "Perplexity"
# ShuttleAI API
# - name: "ShuttleAI"
# apiKey: "${SHUTTLEAI_API_KEY}"
# baseURL: "https://api.shuttleai.app/v1"
# models:
# default: [
# "shuttle-2-turbo",
# "shuttle-turbo",
# "gpt-4o-2024-05-13",
# "gpt-4o",
# "im-also-a-good-gpt2-chatbot",
# "gpt-4-turbo-2024-04-09",
# "gpt-4-turbo",
# "gpt-4-0125-preview",
# "gpt-4-turbo-preview",
# "gpt-4-1106-preview",
# "gpt-4-1106-vision-preview",
# "gpt-4-vision-preview",
# "gpt-4-0613",
# "gpt-4",
# "gpt-4-bing",
# "gpt-4-turbo-bing",
# "gpt-4-32k-0613",
# "gpt-4-32k",
# "gpt-3.5-turbo-0125",
# "gpt-3.5-turbo",
# "gpt-3.5-turbo-1106",
# "claude-3-opus-20240229",
# "claude-3-opus",
# "claude-3-sonnet-20240229",
# "claude-3-sonnet",
# "claude-3-haiku-20240307",
# "claude-3-haiku",
# "claude-2.1",
# "claude-2.0",
# "claude-2",
# "claude-instant-1.2",
# "claude-instant-1.1",
# "claude-instant-1.0",
# "claude-instant",
# "meta-llama-3-70b-instruct",
# "llama-3-70b-instruct",
# "meta-llama-3-8b-instruct",
# "llama-3-8b-instruct",
# "llama-3-sonar-large-32k-online",
# "llama-3-sonar-small-32k-online",
# "llama-3-sonar-large-32k-chat",
# "llama-3-sonar-small-32k-chat",
# "blackbox",
# "blackbox-code",
# "wizardlm-2-8x22b",
# "wizardlm-2-70b",
# "dolphin-2.6-mixtral-8x7b",
# "dolphin-mixtral-8x7b",
# "mistral-large",
# "mistral-next",
# "mistral-medium",
# "mistral-small",
# "mistral-tiny",
# "mixtral-8x7b-instruct-v0.1",
# "mixtral-8x7b-instruct",
# "mixtral-8x22b-instruct-v0.1",
# "mixtral-8x22b-instruct",
# "mistral-7b-instruct-v0.2",
# "mistral-7b-instruct-2",
# "mistral-7b-instruct-v0.1",
# "mistral-7b-instruct",
# "nous-hermes-2-mixtral-8x7b",
# "gemini-1.5-pro-latest",
# "gemini-1.5-pro",
# "gemini-1.0-pro-latest",
# "gemini-1.0-pro",
# "gemini-pro",
# "gemini-1.0-pro-vision",
# "gemini-pro-vision",
# "lzlv-70b",
# "figgs-rp",
# "cinematika-7b"
# ]
# fetch: true
# titleConvo: true
# titleMethod: "completion"
# titleModel: "shuttle-2-turbo"
# summarize: false
# summaryModel: "shuttle-2-turbo"
# forcePrompt: false
# dropParams: ["user", "frequency_penalty", "presence_penalty", "repition_penalty"]
# modelDisplayLabel: "ShuttleAI"
# - name: "together.ai"
# apiKey: "${TOGETHERAI_API_KEY}"
# baseURL: "https://api.together.xyz"
# models:
# default: [
# "zero-one-ai/Yi-34B-Chat",
# "Austism/chronos-hermes-13b",
# "DiscoResearch/DiscoLM-mixtral-8x7b-v2",
# "Gryphe/MythoMax-L2-13b",
# "lmsys/vicuna-13b-v1.5",
# "lmsys/vicuna-7b-v1.5",
# "lmsys/vicuna-13b-v1.5-16k",
# "codellama/CodeLlama-13b-Instruct-hf",
# "codellama/CodeLlama-34b-Instruct-hf",
# "codellama/CodeLlama-70b-Instruct-hf",
# "codellama/CodeLlama-7b-Instruct-hf",
# "togethercomputer/llama-2-13b-chat",
# "togethercomputer/llama-2-70b-chat",
# "togethercomputer/llama-2-7b-chat",
# "NousResearch/Nous-Capybara-7B-V1p9",
# "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
# "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
# "NousResearch/Nous-Hermes-Llama2-70b",
# "NousResearch/Nous-Hermes-llama-2-7b",
# "NousResearch/Nous-Hermes-Llama2-13b",
# "NousResearch/Nous-Hermes-2-Yi-34B",
# "openchat/openchat-3.5-1210",
# "Open-Orca/Mistral-7B-OpenOrca",
# "togethercomputer/Qwen-7B-Chat",
# "snorkelai/Snorkel-Mistral-PairRM-DPO",
# "togethercomputer/alpaca-7b",
# "togethercomputer/falcon-40b-instruct",
# "togethercomputer/falcon-7b-instruct",
# "togethercomputer/GPT-NeoXT-Chat-Base-20B",
# "togethercomputer/Llama-2-7B-32K-Instruct",
# "togethercomputer/Pythia-Chat-Base-7B-v0.16",
# "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
# "togethercomputer/RedPajama-INCITE-7B-Chat",
# "togethercomputer/StripedHyena-Nous-7B",
# "Undi95/ReMM-SLERP-L2-13B",
# "Undi95/Toppy-M-7B",
# "WizardLM/WizardLM-13B-V1.2",
# "garage-bAInd/Platypus2-70B-instruct",
# "mistralai/Mistral-7B-Instruct-v0.1",
# "mistralai/Mistral-7B-Instruct-v0.2",
# "mistralai/Mixtral-8x7B-Instruct-v0.1",
# "teknium/OpenHermes-2-Mistral-7B",
# "teknium/OpenHermes-2p5-Mistral-7B",
# "upstage/SOLAR-10.7B-Instruct-v1.0"
# ]
# fetch: false
# titleConvo: true
# titleModel: "togethercomputer/llama-2-7b-chat"
# summarize: false
# summaryModel: "togethercomputer/llama-2-7b-chat"
# forcePrompt: false
# modelDisplayLabel: "together.ai"
azureOpenAI:
# Endpoint-level configuration
titleModel: "current_model"
plugins: false
assistants: false
groups:
# Group-level configuration
- group: "default"
apiKey: "${DTA_Azure_OpenAIKey}"
instanceName: "${DTA_Azure_OpenAI_InstanceName}"
version: "2023-03-15-preview"
baseURL: "${DTA_Azure_OpenAI_BaseURL}"
# Model-level configuration
models:
gpt-4-vision-preview:
deploymentName: gpt-4-vision-preview
version: "2024-03-01-preview"
gpt-3.5-turbo:
deploymentName: gpt-35-turbo
gpt-4-1106-preview:
deploymentName: gpt-4-1106-preview