AdityaPS/SpaceLLM_Single_Turn_QA

SpaceLLM Single Turn QA — LoRA Adapter for Single-Turn Instruction Following

SpaceLLM Single Turn QA is a parameter-efficient LoRA adapter fine-tuned on top of openai/gpt-oss-20b for single-turn question answering and instruction following. Only the attention projection layers (q_proj, k_proj, v_proj, o_proj) are trained; the full transformer backbone remains frozen, keeping the adapter extremely lightweight while steering the model's outputs toward accurate, focused single-turn responses.

---

Model Details

Model Description

• Developed by: AdityaPS
• Model type: LoRA adapter (PEFT) over a causal language model
• Base model: openai/gpt-oss-20b (22B params, BF16/MXFP4)
• Language(s): English
• License: Apache 2.0
• Task: Causal LM / single-turn question answering, instruction following

Adapter Configuration

Parameter	Value
PEFT type	LoRA
Rank (r)	16
Alpha	32
Dropout	0.05
Target modules	q_proj, k_proj, v_proj, o_proj
Bias	none
Task type	CAUSAL_LM
PEFT version	0.19.1

---

How to Get Started

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "openai/gpt-oss-20b"
adapter_id = "AdityaPS/SpaceLLM_Single_Turn_QA"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base_model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto")
model = PeftModel.from_pretrained(base_model, adapter_id)

prompt = "Your question here"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

Training Details

This adapter was trained using LoRA on the attention projection layers only, keeping the base model frozen. This makes the adapter lightweight to store and share while adapting the model's behavior for single-turn Q&A and instruction-following tasks.

---

Framework Versions

• PEFT 0.19.1