aungkomyint/tara1.2-quest · Hugging Face

Log In<br>Sign Up

","eos_token":"","pad_token":"","unk_token":""}},"createdAt":"2026-06-21T15:33:47.000Z","discussionsDisabled":false,"discussionsSorting":"recently-created","downloads":0,"downloadsAllTime":0,"id":"aungkomyint/tara1.2-quest","isLikedByUser":false,"availableInferenceProviders":[],"showHuggingChatEntry":false,"inference":"","lastModified":"2026-06-21T15:33:57.000Z","likes":0,"pipeline_tag":"text-generation","library_name":"transformers","librariesOther":[],"trackDownloads":true,"model-index":null,"private":false,"repoType":"model","gated":false,"tags":["transformers","safetensors","llama","text-generation","causal-lm","question-generation","json","educational","tiny-llm","tara","en","base_model:aungkomyint/tara1.1","base_model:finetune:aungkomyint/tara1.1","license:apache-2.0","text-generation-inference","endpoints_compatible","region:us"],"tag_objs":[{"id":"text-generation","label":"Text Generation","type":"pipeline_tag","subType":"nlp"},{"id":"transformers","label":"Transformers","type":"library"},{"id":"safetensors","label":"Safetensors","type":"library"},{"id":"en","label":"English","type":"language"},{"id":"llama","label":"llama","type":"other","clickable":true},{"id":"causal-lm","label":"causal-lm","type":"other","clickable":true},{"id":"question-generation","label":"question-generation","type":"other","clickable":true},{"id":"json","label":"json","type":"other","clickable":true},{"id":"educational","label":"educational","type":"other","clickable":true},{"id":"tiny-llm","label":"tiny-llm","type":"other","clickable":true},{"id":"tara","label":"tara","type":"other","clickable":true},{"id":"base_model:aungkomyint/tara1.1","label":"base_model:aungkomyint/tara1.1","type":"other","clickable":true},{"id":"base_model:finetune:aungkomyint/tara1.1","label":"base_model:finetune:aungkomyint/tara1.1","type":"other","clickable":true},{"id":"text-generation-inference","label":"text-generation-inference","type":"other","clickable":true},{"id":"endpoints_compatible","label":"Inference Endpoints","type":"other","clickable":true},{"id":"license:apache-2.0","label":"apache-2.0","type":"license"},{"type":"region","label":"🇺🇸 Region: US","id":"region:us"}],"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"text-generation","processor":"AutoTokenizer"},"widgetData":[{"text":"My name is Julien and I like to"},{"text":"I like traveling by train because"},{"text":"Paris is an amazing place to visit,"},{"text":"Once upon a time,"}],"safetensors":{"parameters":{"F32":4987136},"total":4987136,"sharded":false,"totalFileSize":19954576},"hasBlockedOids":false,"region":"us","isQuantized":false},"discussionsStats":{"closed":0,"open":0,"total":0},"query":{},"inferenceContextData":{"billableEntities":[],"entityName2Providers":{}},"hasQuantizations":false,"copyToBucketNamespaces":[]}">

Tara 1.2 Quest

Tara 1.2 Quest is a tiny experimental question-generation model. It is the successor experiment to aungkomyint/tara1.1, with the task narrowed to producing JSON question lists for a user topic, keyword, sentence, or short request.

The model is designed to answer in this shape:

{"questions":["...","...","..."]}

It is not a general chat assistant. It is a small research model for structured question generation.

Model Details

Model name: tara1.2-quest

Internal checkpoint: tara-1.2-quest-assistant-7c-json-base4v2

Architecture: LlamaForCausalLM

Approximate size: 5M parameters

Context length: 512 tokens

Vocabulary size: 4,108

Weights format: safetensors

License: Apache-2.0

Intended Use

Use this model to generate exploratory questions from a topic or short prompt.

Examples:

cooking

how to smile

starting a small business

database migration risk

how should I think about learning biology?

The expected output is JSON with a questions array.

Quick Start

import json<br>import torch<br>from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "aungkomyint/tara1.2-quest"

tokenizer = AutoTokenizer.from_pretrained(repo_id)<br>model = AutoModelForCausalLM.from_pretrained(repo_id)<br>model.eval()

def generate_questions(user_text):<br>prompt = f"User: {user_text.strip()}\nAssistant:\n"<br>inputs = tokenizer(prompt, return_tensors="pt")<br>inputs.pop("token_type_ids", None)

with torch.no_grad():<br>output = model.generate(<br>**inputs,<br>max_new_tokens=160,<br>do_sample=True,<br>temperature=0.7,<br>top_p=0.9,<br>repetition_penalty=1.18,<br>pad_token_id=tokenizer.pad_token_id,<br>eos_token_id=tokenizer.eos_token_id,

text = tokenizer.decode(output[0], skip_special_tokens=True)<br>reply = text.split("Assistant:", 1)[-1].strip()<br>return reply

reply = generate_questions("cooking")<br>print(reply)

try:<br>data = json.loads(reply)<br>print("question count:", len(data.get("questions", [])))<br>except json.JSONDecodeError:<br>print("Model did not return valid JSON for this sample.")

Example Output

Prompt:

User: cooking<br>Assistant:

Sample output:

"questions": [<br>"What constraints around time, money, energy,...