Instructions to use Medyassino/LLMdocument-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Medyassino/LLMdocument-v3 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B") model = PeftModel.from_pretrained(base_model, "Medyassino/LLMdocument-v3") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Medyassino/LLMdocument-v3: direct link, hf CLI and curl.
- Browser
- Download file 685 Bytes
-
https://huggingface.co/Medyassino/LLMdocument-v3/resolve/main/README.md
- Command line
-
hf download hf://Medyassino/LLMdocument-v3/README.md
-
curl -L -o README.md https://huggingface.co/Medyassino/LLMdocument-v3/resolve/main/README.md
685 Bytes
metadata
base_model: Qwen/Qwen3-4B
library_name: peft
language:
- fr
tags:
- lora
- peft
- document-management
LLMdocument-v3
Adaptateur LoRA pour Qwen/Qwen3-4B : assistant dédié à la gestion documentaire et à l'archivage
(réponses ancrées dans le document, « Information non disponible », refus hors domaine).
Utilisation
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
tok = AutoTokenizer.from_pretrained("Medyassino/LLMdocument-v3")
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B", device_map="auto", torch_dtype="auto")
model = PeftModel.from_pretrained(base, "Medyassino/LLMdocument-v3").eval()