Instructions to use DimplePavithra/pavithravd-resumebot-flan-t5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DimplePavithra/pavithravd-resumebot-flan-t5 with Transformers:

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

pipe = pipeline("text-generation", model="DimplePavithra/pavithravd-resumebot-flan-t5")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DimplePavithra/pavithravd-resumebot-flan-t5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DimplePavithra/pavithravd-resumebot-flan-t5 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DimplePavithra/pavithravd-resumebot-flan-t5

SGLang

How to use DimplePavithra/pavithravd-resumebot-flan-t5 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 "DimplePavithra/pavithravd-resumebot-flan-t5" \
    --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": "DimplePavithra/pavithravd-resumebot-flan-t5",
		"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 "DimplePavithra/pavithravd-resumebot-flan-t5" \
        --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": "DimplePavithra/pavithravd-resumebot-flan-t5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DimplePavithra/pavithravd-resumebot-flan-t5 with Docker Model Runner:
```
docker model run hf.co/DimplePavithra/pavithravd-resumebot-flan-t5
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

ResumeBot — PavithraVD

ResumeBot is an academic project built with FLAN-T5 and a TF-IDF retriever.

It answers questions about PavithraVD's resume by retrieving relevant resume facts and giving those facts to the fine-tuned sequence-to-sequence model.

Model

Base model: google/flan-t5-small for the CPU version used in this project
Framework: Hugging Face Transformers
Retrieval: TF-IDF + cosine similarity
Interface: Gradio

Repository files

README.md — model card and project documentation
app.py — Gradio application
requirements.txt — dependencies for the Space/app
resume_qa_dataset.csv — training/validation question-answer data
resume.txt — resume text used by the project
config.json — model architecture configuration
model.safetensors or pytorch_model.bin — fine-tuned model weights
tokenizer.json — tokenizer data
tokenizer_config.json — tokenizer configuration
special_tokens_map.json — special-token mapping
spiece.model — SentencePiece model used by T5
generation_config.json — generation defaults, if produced

The model/tokenizer files are generated by model.push_to_hub() and tokenizer.push_to_hub().

Run locally

pip install -r requirements.txt
python app.py

Notes

The fine-tuned model is intended to answer resume-related questions. The application uses TF-IDF retrieval to select relevant resume facts before generation.

If the repository is deployed as a Hugging Face Space, set the Space SDK to Gradio.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for DimplePavithra/pavithravd-resumebot-flan-t5

Base model

google/flan-t5-small

Finetuned

(523)

this model