Instructions to use Pravesh390/flan-t5-finetuned-wrongqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pravesh390/flan-t5-finetuned-wrongqa with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Pravesh390/flan-t5-finetuned-wrongqa")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Pravesh390/flan-t5-finetuned-wrongqa")
model = AutoModelForSeq2SeqLM.from_pretrained("Pravesh390/flan-t5-finetuned-wrongqa", device_map="auto")

PEFT
How to use Pravesh390/flan-t5-finetuned-wrongqa with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pravesh390/flan-t5-finetuned-wrongqa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pravesh390/flan-t5-finetuned-wrongqa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pravesh390/flan-t5-finetuned-wrongqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Pravesh390/flan-t5-finetuned-wrongqa

SGLang

How to use Pravesh390/flan-t5-finetuned-wrongqa with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Pravesh390/flan-t5-finetuned-wrongqa" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pravesh390/flan-t5-finetuned-wrongqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Pravesh390/flan-t5-finetuned-wrongqa" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pravesh390/flan-t5-finetuned-wrongqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Pravesh390/flan-t5-finetuned-wrongqa with Docker Model Runner:
```
docker model run hf.co/Pravesh390/flan-t5-finetuned-wrongqa
```

Pravesh390 commited on Jul 18, 2025

Commit

292a6dc

verified ·

1 Parent(s): 83271aa

Training in progress, epoch 1

Browse files

Files changed (3) hide show

README.md +46 -30
adapter_model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,40 +1,56 @@
-# 🤖 FLAN-T5 Fine-Tuned with LoRA on Hallucinated QA Dataset
-## 🧠 Model Description
-This is a fine-tuned `google/flan-t5-base` model using [LoRA (Low-Rank Adaptation)](https://arxiv.org/abs/2106.09685) for efficient training on a small, adversarial QA dataset meant to test hallucination.
-## 🔍 Intended Uses
-- Research on hallucination and robustness in language models
-- Education and demonstration of LoRA + Hugging Face pipelines
-- Benchmarking models on confusing or misleading inputs
-## ⚠️ Limitations
-- Not trained on factual or large QA corpora
-- Not production-ready; may output hallucinated or nonsensical answers
-## 🧪 Training Setup
-- LoRA: `r=16`, `alpha=32`, `dropout=0.1`
-- 3 Epochs, Batch size 4, LR: 5e-5
-- Model: `flan-t5-base` + LoRA
-- Platform: Google Colab (T4)
-- Logging: Weights & Biases
-## 📚 Dataset
-Custom QA dataset containing 90+ rephrased versions of 15 blockchain/web3 questions, each with intentionally wrong answers.
-👉 [Dataset on Hugging Face Hub](https://huggingface.co/datasets/Pravesh390/qa_wrong_data)
-## 💡 How it works
-- Tokenized inputs: max length 64
-- Output (labels): max length 16
-- Hugging Face `Trainer` + LoRA from `peft`
-## 👤 Author
-Pravesh Saini
-🔗 [Hugging Face](https://huggingface.co/Pravesh390)
-## 🏷️ Tags
-`flan-t5` `lora` `peft` `qa` `hallucination` `finetune` `transformers`
-## 📄 License
-MIT

+---
+library_name: peft
+license: apache-2.0
+base_model: google/flan-t5-base
+tags:
+- base_model:adapter:google/flan-t5-base
+- lora
+- transformers
+model-index:
+- name: flan-t5-finetuned-wrongqa
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# flan-t5-finetuned-wrongqa
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+### Training results
+### Framework versions
+- PEFT 0.16.0
+- Transformers 4.53.2
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.2

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd733809a81d5c422fc45cad74d601e9991018d848926de6e44862530278ab8
 size 7098016

 version https://git-lfs.github.com/spec/v1
+oid sha256:21f2e56ccc599bc25444156203b96f6333249ada930e261f20affaa480ddf92f
 size 7098016

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d3e6aec6d5f3d2366dde0d6eb7d9d8486cc877fb9cda85f79a85551788490e
 size 5368

 version https://git-lfs.github.com/spec/v1
+oid sha256:b8dd618dd6a33463943a33427faae6032a9a05bfce11c8a6e69220162fe35e70
 size 5368