ModelVérifiéExterne

Led Proposed Qa Mistral 7b LoRA

LoRA adapter fine-tuned on F1 technical regulations QA.

Sourcehuggingface.co/Roseshmay/led-qa-mistral-7b-lora/tree/021a310a46181faf8da3e49419ac6af267e35505

TypeLoRAModèle de basemistralai/Mistral-7B-Instruct-v0.3VersionRevision 021a310Éditeur@RoseshmayCClasse

Source du modèle

Type: LoRA
Taille du fichier: 160 MB
Modèle de base: mistralai/Mistral-7B-Instruct-v0.3
Version: vRevision 021a310
Mis à jour: 3 oct. 2026
Éditeur: @Roseshmay
Téléchargements: 9
Paramètres: 7B
Tâches: Génération de texte
Source: Hugging Face

Description de la source

LED QA LoRA — Mistral-7B-Instruct

LoRA adapter fine-tuned on F1 technical regulations QA.

Base model

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

Training

Dataset: filtered/full Proposed QA SFT split
LoRA r=16, alpha=32, target=all linear projections
Epochs: 3
Max seq len: 2048

Load

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "mistralai/Mistral-7B-Instruct-v0.3"
adapter = "REPO_ID"

tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base,
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter)

Sources

1 source

Hugging FacePrincipalVersion 021a310a46181faf8da3e49419ac6af267e35505

huggingface.co/Roseshmay/led-qa-mistral-7b-lora/tree/021a310a46181faf8da3e49419ac6af267e35505

Vérifié 3 oct.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 160 MB · SHA-256 130f56151819…3266 · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme11 juil.huggingface.co/Roseshmay/led-qa-mistral-7b-lora

--- library_name: peft base_model: mistralai/Mistral-7B-Instruct-v0.3 tags: - lora - qa - f1-regulations - led pipeline_tag: text-generation --- # LED QA LoRA — Mistral-7B-Instruct LoRA adapter fine-tuned on **F1 technical regulations QA**. ## Base model `mistralai/Mistral-7B-Instruct-v0.3` ## Training - Dataset: `filtered/full` Proposed QA SFT split - LoRA r=16, alpha=32, target=all linear projections - Epochs: 3 - Max seq len: 2048 ## Load ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer base = "mistralai/Mistral-7B-Instruct-v0.3" adapter = "REPO_ID" tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( base, device_map="auto", torch_dtype="auto", trust_remote_code=True, ) model = PeftModel.from_pretrained(model, adapter) ```

Note3 oct.huggingface.co/Roseshmay/led-qa-mistral-7b-lora

Source context: 9 downloads · 0 likes · Pipeline text-generation · Library peft · Repo Roseshmay/led-qa-mistral-7b-lora

Note11 juil.huggingface.co/Roseshmay/led-qa-mistral-7b-lora

Source context: 19 downloads · 0 likes · Pipeline text-generation · Library peft · Repo Roseshmay/led-qa-mistral-7b-lora