HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Mistral-7B-Instruct-v0.3

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

kind
original
quant
bf16 (16-bit)
family
mistral
modality
—
root model
mistralai/Mistral-7B-v0.3
provider
mistralai
license
apache-2.0
language
—
context
—
library
vllm
vRAM (GB)
—
size on disk
—
downloads
5,586,406
likes
2,728
created
—
last modified
2025-12-03T12:13:48+00:00 (2025)
huggingface
https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
tags
vllmsafetensorsmistralmistral-commonbase_model:mistralai/Mistral-7B-v0.3base_model:finetune:mistralai/Mistral-7B-v0.3license:apache-2.0region:usdeploy:sagemaker

Benchmark scores (0)

no scores extracted for this variant.

Discussions (210)

titleauthorstatuscommentstype
Language ListeNVy1981open0disc
Multilingual powerhouse — testing for mobile deployment3morixdopen0disc
TemporalMesh Transformer: 29.4 PPL at 48% compute — dynamic graph attention + adaptive exit gates (open-source, 226 tests)vigneshwar234open0disc
Cross-architecture RYS sweep — Mistral-7B-Instruct-v0.3 (same circuit-position as Llama-3.1-8B; weaker baseline → 28 boosters)john-broadwayopen0disc
give me api keyreaabon3open0disc
Update README.mddarthcrawlclosed0disc
Request: DOImilezdeep13open0disc
Request: DOIshrinivaspatilopen0disc
calculatorsaivikas1703draft0disc
Request: DOIsoroarkmsesclosed0disc
Fix adding system prompt in chat_templatemspanrinopen0disc
Hitung EV parlay 1.47×1.35×1.17Mauza182open0disc
Request: AccessMartiiniiiopen0disc
Configurationchrismerveilclosed0disc
[RFC] The End of Dead Internet: A Proposal for Bilateral Optimizationlomax3open0disc
[RFC] The End of Dead Internet: A Proposal for Bilateral Optimizationlomax3open0disc
Request AccessJosh2404open0disc
gow can i get an api key of this aiinakiag2open0disc
AccessVetal50open0disc
Request: DOImukund27open0disc
Lightweight deployment for edge devicesCagnicolasopen0disc
Testingnitesh0306open0disc
Request: DOIzaryab199open0disc
Request AccessJamie47open0disc
Request: DOIMike4707open0disc
Request accessida-adaopen0disc
Request accesshanam197open0disc
Request accessGhufranAIopen0disc
Request accessgyamotabopen0disc
request accessmeda4everopen0disc
Request accessValdrykopen0disc
Request:DOIprime25closed0disc
Request: DOIm0r14rtyclosed0disc
Adding `transformers` as the library nameariG23498open0disc
Request: DOIboboba86open0disc
Request: DOIAdorisopen0disc
Request: DOI for Mistral-7B-Instruct-v0.3Dovydas1337open0disc
Request: DOIDimpal07open0disc
request Accessfro01open0disc
request accesArt4dotFreeopen0disc
Request Access to the Modelchareszopen0disc
doc-generatorDev-Gosuitsdraft0disc
access to the modelkrys0open0disc
Request for access to the modelCompetentCoderopen0disc
Update README.mdmayank877open0disc
Request: DOImayank877open0disc
repo_id="mistralai/Mistral-7B-Instruct-v0.2" model is not workingAniket58-techopen0disc
mistralmalinours17draft0disc
Request: DOIasomiddinsaidov07open0disc
mistral _fine_tune1shogun07draft0disc
Request to Access the ModelRolfo-Cattaneoopen0disc
Request Access to the modellucabar21open0disc
testandrey0572draft0disc
access to the model "Mistral-7B-Instruct-v0.3"Adamsyaraopen0disc
Requesting Access to Mistral-7B-Instruct-v0.3sporwalopen0disc
Machine 4060 testhmntmallahdraft0disc
Request: DOIpeter-rgopen0disc
Mistral for PoCrajeev1sdraft0disc
Request: DOIScott-McCall1715open0disc
Request: DOIsteng0open0disc
Request: DOICR33113696open0disc
Request: DOI Request access to modelsnnnunvropen0disc
with 2 partrakmikopen0disc
Create instruction_tuning_800.jsonlZynaraopen0disc
pullMustafaQadandraft0disc
Please remove my access to this modelManiWaghclosed0disc
Invalid credentials in Authorization headerchatterjeeabhishek0112open0disc
my_firstkvinay7draft0disc
MistralReady2Learn2025draft0disc
Request: DOImetfalanopen0disc
Help a Student: How to Deploy My Fine-Tuned Model for Free?riakrstopen0disc
Requesting Access to Mistral-7B for Experimental and Personal Project (Non-Commercial Use)danishhereopen0disc
trialulasPAUdraft0disc
Mistral output get's stuck in a loop for this input.kashifoopen0disc
Mistral-7B-Instruct-v0.3 to Run Locally on Windows PC Without NVIDIA GPUmbettopen0disc
Endpoint Not Workingrandr000open0disc
pleaseKasharsdraft0disc
Request: DOIfrozonDynamoclosed0disc
Test MistralVedant1009draft0disc
Not Supporting for Text Generationshvmsnhaopen0disc
Bad Request: The endpoint is paused, ask a maintainer to restart it\"}"tanujg78open0disc
Request for accessAbhin12open0disc
Request: DOIpadish02closed0disc
"Bad Request: Your endpoint is in error, check its status on endpoints.huggingface.cotanujg78open0disc
Request for Access to Mistral 0.3 Model Weights and TokenizerCode-fyopen0disc
Documentation for inference API Endpointsatlas-ai-naveenopen0disc
Debate ArenaAryan-Ghadekardraft0disc
Not properly tool calling after instruct fine-tuningtom4sgopen0disc
Request: DOIRahasia145open0disc
D:\huggingfacedatacelltariqdraft0disc
Request: DOIOloneopen0disc
Request: DOIRizkiananda90open0disc
blipParthV42draft0disc
Unable to serve mistralai/Mistral-7B-Instruct-v0.3 using vllmAbdulQadeer09open0disc
Request: DOIBlakdogopen0disc
Request: DOIHanwen9560open0disc
Upload faqs.txtflx1masterpieceopen0disc
Problemn with spanish accentsrpmprimaopen0disc
Suddenly I am getting "Model not found"tanujg78open0disc
Request: DOInono9595263open0disc
Update README.mdSuluBaykusopen0disc
Request: DOIbyanshaheenopen0disc
Request: DOILinkoDNopen0disc
Request: DOIteczo63open0disc
An stable Output with Mistral-7b-Instruct-v0.3securis360open0disc
Request: DOIbbttuttjtjjtopen0disc
Update README.mdHardbanRecordsLabopen0disc
Request: DOIumarjan11open0disc
Access the Modelumarjan11open0disc
Request: DOIhuyumeopen0disc
Request: DOIZaia98open0disc
Local ollama llmJediBendudraft0disc
Request for access to the modellazylabraopen0disc
Request for Access to Mistral-7B-Instruct ModelPaulieScanlonopen0disc
Update README.mdsunalibhattacherjiopen0disc
How can I embed textual input to calculate the cosine similarity?skaesopen0disc
Request for Access to Mistral-7B-Instruct-v0.3 for Research and Development in Large-Scale Text ProcessingUnadumandaopen0disc
Request: DOISehajbiropen0disc
version CXXABI_1.3.8 not found errorsamagaiopen0disc
rag with mistralrakmikopen0disc
How do I access this model in google colab?VikramanHFopen0disc
Error with using AutoTokenizer to loadthuzhizhiclosed0disc
block_sizesdyyopen0disc
correct numberssdyyopen0disc
regarding error icon popping.Bhaskar2611open0disc
any times i am getting empty responses from the LLMharikrishnan99open0disc
sliding_window is null?haili-tianclosed0disc
getting HfHubHTTPError: 422 client errorharikrishnan99closed0disc
Accuracy Scoresfbkhggngfaceopen0disc
Can't install mistral-inference 1.3.1Nahieliopen0disc
Sentence piece -- tokenizer problemNahieliopen0disc
about model?LogeshLogeshclosed0disc
HuggingfaceEndpointalpcansoydasopen0disc
Broken tokenizeranfericoclosed0disc
Clean up tool use snippetRocketknight1merged0disc
It seems like there is server overload or downtime of upstream ?prithivMLmodsclosed0disc
Facing Gateway ErrorRohith8789open0disc
Add base_model metadatadavanstrienmerged0disc
trying on comfyui but there are 3 filessss251open0disc
All parameters finetune,OOMSaicyopen0disc
Fix chat template when tool_calls is defined but NoneRocketknight1merged0disc
Upload tokenizerRocketknight1closed0disc
Add tool calling support to chat templateRocketknight1merged0disc
Delete config.jsontitiyuopen0disc
My "silly" experiment.ZeroWwopen0disc
Update README.mdRocketknight1merged0disc
Problem with inference endpoint.goporoopen0disc
Why here exists two checkpoints?OkayestProgrammerclosed0disc
Update README.mdeulerclosed0disc
My alternative quantizations.ZeroWwopen0disc
Space in chat_templateThangLD201open0disc
Update README.mdpys11open0disc
Command Line mistral-chat performs better than ChatCompletionRequest on the same text ?maniiiiopen0disc
Conversation roles must alternate user/assistant/user/assistant/...akanksh-bcopen0disc
Inconsistent Response Format for Inference Chat Completion EndpointMrGeniusProgrammeropen0disc
Align tokenizer with mistral-commonyys-yssclosed0disc
Permission error for Mistral-7B-Instruct-v0.3ladn-ghasemiopen0disc
Deploying a fine-tuned model with custom inference codemaz-qualtricsopen0disc
plz wantdnehate2022draft0disc
Align tokenizer with mistral-commonRocketknight1merged0disc
Loss is increasing while finetuningabpani1994open0disc
[AUTO] CVST Tokenizer Badgerpandora-smerged0disc
[AUTO] CVST Tokenizer Badgerpandora-sclosed0disc
MistralTokenizer with HuggingFacePipeline.from_model_idjsemrauopen0disc
[AUTO] CVST Tokenizer Badgerpandora-sclosed0disc
[AUTO] CVST Tokenizer Badgerpandora-sclosed0disc
Updating chat template, trying to make it match with `mistral_common`pandora-smerged0disc
How to do batch processing with Mistral 7B?hyperiontauopen0disc
Is this model open weight or open sourceShreyas94open0disc
Request: DOIdsevyclosed0disc
Please check these quantizations.ZeroWwopen0disc
default parameters for model.generatechristinagottschopen0disc
Support tool_use chat_templatemadroidopen0disc
Update Chat Template - V3 Tokenizerpandora-sclosed0disc
Tool calling is supported by ChatLLM.cppJ22open0disc
Support tool calling in TransformersRocketknight1open0disc
Direct Hugging Face Inference API function callinglamdaoopen0disc
tokenizer.default_chat_template containing "true == false"maumaropen0disc
Mistral-Inference packageswtbopen0disc
Unconsolidated tensorsT9ALXD9open0disc
How to enable streaming?Alexander-Minushkinopen0disc
Thank you for the powerful open source model, but I would like to know how to use function_call in TransformersNSSSJSSopen0disc
This model is censored, don't bother with it.seedmancopen0disc
Update README.mdCordobianopen0disc
Hallucinating function callsSebastianSopen0disc
Inconsistent parallel function callingSebastianSopen0disc
problems when use mistral-chatjinglishi0206open0disc
Limited (truncated) response with inference APIRobertTayloropen0disc
Slow tokenizer problem.bradhutchingsopen0disc
feat/tools-in-chat-templatelcahillopen0disc
Not generating [TOOL_CALLS]ShukantPopen0disc
Problems deploying to SageMakerliam-smithopen0disc
Is the model uncensored?jujutechnologyopen0disc
thanks and question function-calling.NickyNickyopen0disc
You are truly a godsend!lcahillclosed0disc
tokenizer.model and tokenizer.model.v3 are identicalwolframopen0disc
no system message?mclassHF2023open0disc
Update README.mddejanseoopen0disc
Thanks. 0.3 Can Do More Than 0.1 & 0.2.deletedclosed0disc
Which PAD token can be used?VlSavopen0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.