Instructions to use tunachiu/llm_adapter_text_correction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tunachiu/llm_adapter_text_correction with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "tunachiu/llm_adapter_text_correction") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from tunachiu/llm_adapter_text_correction: direct link, hf CLI and curl.
- Browser
- Download file 960 Bytes
-
https://huggingface.co/tunachiu/llm_adapter_text_correction/resolve/main/README.md
- Command line
-
hf download hf://tunachiu/llm_adapter_text_correction/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/tunachiu/llm_adapter_text_correction/resolve/main/README.md
960 Bytes
metadata
base_model: Qwen/Qwen3.5-4B
library_name: peft
language: vi
tags:
- lora
- asr-correction
llm_adapter_text_correction
LoRA adapter (rank 8, alpha 16) for Qwen/Qwen3.5-4B that corrects the ASR transcript of one user turn.
- Input (user message): conversation context (time, location, profile), earlier turns, the ASR text, then an instruction to fix spelling errors only, staying close to the ASR text; it may add "." and "," between clauses, capitalise proper names and write digits or symbols (times, amounts, phone numbers, emails).
- Output: the corrected text only. Use with thinking off (
chat_template_kwargs={"enable_thinking": false}), greedy decoding. - Training: 20k pairs (ASR text -> true text), real transcripts plus synthetic ASR noise; 1 epoch, lr 2e-4.
Serving with vLLM as a LoRA module:
vllm serve Qwen/Qwen3.5-4B --enable-lora --max-lora-rank 64 --lora-modules text_correction=tunachiu/llm_adapter_text_correction