Mistral 7B Instruct v0.3

Fiche de référence du modèle Mistral 7B Instruct v0.3 publié par Mistral AI : 7 milliards de paramètres, licence Apache 2.0, appel de fonctions.

Specifications

Hardware requirements

Usage and languages

Languages : English, French

Chat template : mistral

Intended uses

Assistant généraliste, extraction d'informations, appel de fonctions (function calling), base de fine-tuning.

Known limitations

Pas de mécanisme de modération intégré. Moins précis que les grands modèles sur le raisonnement complexe.

Evaluations and version

Version 0.3 · Released on : 2024-05-22

Notes

Modèle publié par Mistral AI, référencé ici pour servir de base aux configurations LoRA du catalogue. ContexteTech ne l'a pas modifié.

Cost to run this model

License

€0 license fee (Apache 2.0)

Required GPU memory

16 Go

CPU only (no GPU)

no

Rental prices excluding VAT, 1-GPU instance, 730 hours a month, as of September 29, 2026 (RunPod and Lambda in dollars, converted at the ECB rate). An open model has no per-call cost: you pay for the hardware that runs it.

Identifier

contextetech--mistral-7b-instruct-v0.3

Type

LLM · Fine-tune

File

mistral-7b-instruct-v0.3.model.json

Format

JSON (application/json)

Size

628 bytes

Encoding

UTF-8

Estimated tokens

≈ 173

Language

Multilingual

License

Apache 2.0

Commercial use

Allowed

Version

0.3

Published on

September 26, 2026 at 6:12 PM

Updated on

September 30, 2026 at 5:18 PM

Storage

in database

Uses

0

Likes

0

mistral-7b-instruct-v0.3.model.json

{
  "format": "contextetech/model/v1",
  "id": "contextetech/mistral-7b-instruct-v0.3",
  "description": "Fiche de référence du modèle Mistral 7B Instruct v0.3 publié par Mistral AI : 7 milliards de paramètres, licence Apache 2.0, appel de fonctions.",
  "tags": [
    "mistral",
    "7b",
    "open-weights"
  ],
  "license": "Apache-2.0",
  "language": "multi",
  "type": "finetune",
  "baseModel": "mistralai/Mistral-7B-v0.3",
  "family": "mistral",
  "params": "7B",
  "weightsFormat": "safetensors",
  "quant": "",
  "contextLength": 32768,
  "weightsUrl": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3"
}

Download

# https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3

Transformers (Python)

from transformers import AutoModelForCausalLM, AutoTokenizer

path = "./mistral-7b-instruct-v0.3"   # dossier des poids téléchargés
tok = AutoTokenizer.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(path, device_map="auto")
inputs = tok("your input here", return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**inputs, max_new_tokens=200)[0]))

An assistant that answers from your product documentation

Your documentation exists but nobody reads it: customers ask support questions whose answer is already written, and the team spends ages finding the right page.

Step 2 of 4 : Pick a model that runs on your side (If the documentation is confidential)