(function() { var utmInheritingDomain = "appstore.com", utmRegExp = /(&|\?)utm_[A-Za-z]+=[A-Za-z0-9]+/gi, links = document.getElementsByTagName("a"), utms = [ "utm_medium={{URL - utm_medium}}", "utm_source={{URL - utm_source}}", "utm_campaign={{URL - utm_campaign}}" ]; for (var index = 0; index < links.length; index += 1) { var tempLink = links[index].href, tempParts; if (tempLink.indexOf(utmInheritingDomain) > 0) { tempLink = tempLink.replace(utmRegExp, ""); tempParts = tempLink.split("#"); if (tempParts[0].indexOf("?") < 0 ) { tempParts[0] += "?" + utms.join("&"); } else { tempParts[0] += "&" + utms.join("&"); } tempLink = tempParts.join("#"); } links[index].href = tempLink; } }());
Products
Solutions
ModelsPricingUse Cases
Resources
Company
Get started

Browse generative AI models
supported by Friendli Engine

Friendli Engine

Model library

Model architectureModelsHugging Face Hub repos (example)LoRA
ArcticForCausalLM
Arctic

Snowflake/snowflake-arctic-instruct

, etc.
BaichuanForCausalLM
Baichuan

baichuan-inc/Baichuan2-13B-Chat

,

baichuan-inc/Baichuan2-7B-Chat

,
, etc.
BlenderbotForConditionalGeneration
Blenderbot

facebook/blenderbot-3B

BloomForCausalLM
BLOOM BLOOMZ

bigscience/bloom

, etc.
CohereForCausalLM
Command R Command R+

CohereForAI/c4ai-command-r-plus

, etc.
DbrxForCausalLM
DBRX

databricks/dbrx-instruct

, etc.
DeepseekForCausalLM
DeepSeek

deepseek-ai/DeepSeek-V2

ExaoneForCausalLM
EXAONE

LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct

FalconForCausalLM
Falcon

tiiuae/falcon-40b

, etc.
Gemma2ForCausalLM
Gemma 2

google/gemma-2-9b-it

,

google/gemma-2-27b-it

,
, etc.
GemmaForCausalLM
CodeGemma Gemma

google/codegemma-7b-it

,

google/gemma-7b-it

,
, etc.
GPT2LMHeadModel
GPT2

openai-community/gpt2-xl

, etc.
GPTBigCodeForCausalLM
StarCoder SantaCoder

bigcode/starcoder

, etc.
GPTJForCausalLM
GPT-J

EleutherAI/gpt-j-6b

, etc.
GPTNeoXForCausalLM
GPT-NeoX Pythia Dolly StableLM

EleutherAI/gpt-neox-20b

,

databricks/dolly-v2-12b

,
, etc.
Grok1ForCasualLM
Grok-1

xai-org/grok-1

LlamaForCausalLM
Llama 3.1 Llama 3 Llama 2 CodeLlama OpenLLaMA Vicuna Yi WizardLM WizardMath WizardCoder

meta-llama/Meta-Llama-3.1-405B-Instruct

,

meta-llama/Meta-Llama-3-70B-Instruct

,

meta-llama/CodeLlama-70b-hf

,

lmsys/vicuna-13b-v1.3

,

01-ai/Yi-34B

,

WizardLMTeam/WizardLM-70B-V1.0

,
, etc.
MistralForCausalLM
Mistral 7B Mistral Nemo Mistral Large 2 Mathstral

mistralai/Mistral-7B-Instruct-v0.3

,

mistralai/Mistral-Nemo-Instruct-2407

,

mistralai/Mistral-Large-Instruct-2407

,

mistralai/Mathstral-7B-v0.1

,
, etc.
MixtralForCausalLM
Mixtral 8x7B Mixtral 8x22B Zephyr

mistralai/Mixtral-8x22B-Instruct-v0.1

,

mistralai/Mixtral-8x7B-Instruct-v0.1

,

HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1

,
, etc.
MPTForCausalLM
MPT

mosaicml/mpt-30b

, etc.
MT5ForConditionalGeneration
MT5

google/mt5-xxl

, etc.
OPTForcausalLM
OPT

facebook/opt-66b

, etc.
Phi3ForCausalLM
Phi-3.5 Phi-3

microsoft/Phi-3.5-MoE-instruct

,

microsoft/Phi-3-mini-128k-instruct

,
, etc.
PhiForCausalLM
Phi-1 Phi-2

microsoft/phi-2

, etc.
Qwen2ForCausalLM
Qwen1.5 Qwen2

Qwen/Qwen2-72B-Instruct

,

Qwen/Qwen1.5-7B-Chat

,
, etc.
SolarForCausalLM
Solar

upstage/solar-pro-preview-instruct

Starcoder2ForCausalLM
StarCoder 2

bigcode/starcoder2-15b

, etc.
T5ForConditionalGeneration
FLAN-T5

google/flan-t5-xxl

, etc.

Friendli Engine supports a wide array of quantization techniques, including FP8, INT8, and AWQ in all models.
The list above may not exhaustive. If your model does not belong to one of the above models, please check our documentation for more information or contact us for support.

HOW TO USE

Three ways to run generative AI models with Friendli Engine:

01

Friendli Dedicated Endpoints

Build and run generative AI models on autopilot

Learn more

02

Friendli Container

Serve LLMs/LMMs inferences with Friendli Engine in your GPU environment

Learn more

03

Friendli Serverless Endpoints

Call fast and affordable API for open-source generative AI models

Learn more