Who developed Zephyr Tinyllama Sft Qlora and how large is it?

Zephyr Tinyllama Sft Qlora is developed by Ritvik19, a model with 1.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Zephyr Tinyllama Sft Qlora perform on standard benchmarks?

Zephyr Tinyllama Sft Qlora has the following published scores: MMLU 25.85. Compare against reference models on this page or on the LLM Explorer leaderboards.

Zephyr Tinyllama Sft Qlora by Ritvik19

Name: Zephyr Tinyllama Sft Qlora
Author: Ritvik19

Zephyr Tinyllama Sft Qlora is an open-source language model by Ritvik19. Features: 1.1b LLM, License: apache-2.0, LLM Explorer Score: 0.16, Arc: 34.6, HellaSwag: 59.8, MMLU: 25.9, GSM8K: 1.7.

Adapter Alignment-handbook Base model:adapter:tinyllama/t... Base model:tinyllama/tinyllama... Dataset:huggingfaceh4/ultracha... Finetuned Generated from trainer Llama Lora Peft Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/Ritvik19/zephyr-tinyllama-sft-qlora

Zephyr Tinyllama Sft Qlora Parameters and Internals

Model Type

fine-tuned

Additional Notes

Model card automatically generated according to available information from Trainer.

Training Details

Data Sources:

HuggingFaceH4/ultrachat_200k

LLM Name	Zephyr Tinyllama Sft Qlora
Repository 🤗	https://huggingface.co/Ritvik19/zephyr-tinyllama-sft-qlora
Base Model(s)	TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
Model Size	1.1b
Required VRAM	0 GB
Updated	2026-03-29
Maintainer	Ritvik19
Model Files	0.0 GB 0.0 GB
Model Architecture	Adapter
License	apache-2.0
Model Max Length	2048
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj\|down_proj\|k_proj\|up_proj\|o_proj\|gate_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	16

Rank the Zephyr Tinyllama Sft Qlora capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Zephyr Tinyllama Sft Qlora

Best Alternatives	Context / RAM	Downloads
Testing	0K / 0 GB	5
Openhermes Tinyllama Sft Qlora	0K / 0 GB	6
...hyr Tiny Sft Qlora Quantized 2	0K / 0 GB	44
Zephyr Tiny DPO Qlora	0K / 0.1 GB	32
DPO Mcqa V1.02	0K / 0.4 GB	5
DPO Mcqa QuantizedBitsAndBytes	0K / 0.8 GB	5
MCQDPO1	0K / 0 GB	11
Mcqa	0K / 0 GB	5
ProjectElrondMCQv1	0K / 0 GB	6
Tinyllama Cs	0K / 0 GB	5

Note: green Score (e.g. "73.2") means that the model is better than Ritvik19/zephyr-tinyllama-sft-qlora.