Instructions to use Hussnain1/interviewmate-flan-t5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hussnain1/interviewmate-flan-t5-large with Transformers:

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

pipe = pipeline("text-generation", model="Hussnain1/interviewmate-flan-t5-large")

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

tokenizer = AutoTokenizer.from_pretrained("Hussnain1/interviewmate-flan-t5-large")
model = AutoModelForSeq2SeqLM.from_pretrained("Hussnain1/interviewmate-flan-t5-large", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hussnain1/interviewmate-flan-t5-large with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hussnain1/interviewmate-flan-t5-large"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hussnain1/interviewmate-flan-t5-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hussnain1/interviewmate-flan-t5-large

SGLang

How to use Hussnain1/interviewmate-flan-t5-large 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 "Hussnain1/interviewmate-flan-t5-large" \
    --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": "Hussnain1/interviewmate-flan-t5-large",
		"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 "Hussnain1/interviewmate-flan-t5-large" \
        --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": "Hussnain1/interviewmate-flan-t5-large",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hussnain1/interviewmate-flan-t5-large with Docker Model Runner:
```
docker model run hf.co/Hussnain1/interviewmate-flan-t5-large
```

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

InterviewMate: FLAN-T5 Large fine-tuned for interview question generation

Full fine-tune of google/flan-t5-large used in InterviewMate as a fallback question generator: when the main Qwen2.5 LoRA question engine is unavailable or returns too few valid questions, this model writes single interview questions from candidate context (skills, projects, experience).

Training


Base model	google/flan-t5-large (full fine-tune)
Data	answer-aware question generation pairs from SQuAD (QG) and HotpotQA, plus interview pairs built from CV-style contexts, mostly generated and curated by me for InterviewMate (not published)
Input format	`generate question: {answer} context: {context}` (max 512 tokens), beam search 4

How to use

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

repo = "Hussnain1/interviewmate-flan-t5-large"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSeq2SeqLM.from_pretrained(repo)

text = ("generate question: FastAPI RAG backend context: The candidate built a FastAPI backend "
        "that answers questions over company documents with a RAG pipeline.")
ids = tok(text, return_tensors="pt").input_ids
print(tok.decode(model.generate(ids, max_new_tokens=64, num_beams=4)[0], skip_special_tokens=True))

The exact input format used in production is built by _build_t5_context in backend/app/services/question_generator.py of the InterviewMate repo.

Limitations

Generates one question at a time; the Qwen LoRA model is the primary planner.
English only; questions can be generic when the CV context is thin.
For interview practice only.

Author

Muhammad Hussnain Jamil · GitHub · LinkedIn · Portfolio

Downloads last month: 327

Safetensors

Model size

0.8B params

Tensor type

F32

Model tree for Hussnain1/interviewmate-flan-t5-large

Base model

google/flan-t5-large

Finetuned

(224)

this model

Hussnain1
/

interviewmate-flan-t5-large