What are the hardware requirements for Starcoderbase Triviaqa?

Starcoderbase Triviaqa requires approximately 62.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Starcoderbase Triviaqa and how large is it?

Starcoderbase Triviaqa is developed by vwxyzjn, a model with 15.5b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Starcoderbase Triviaqa?

Starcoderbase Triviaqa is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Starcoderbase Triviaqa by vwxyzjn — VRAM 62.1GB

Name: Starcoderbase Triviaqa
Author: vwxyzjn

Starcoderbase Triviaqa is an open-source language model by vwxyzjn. Features: 15.5b LLM, VRAM: 62.1GB, License: bigscience-openrail-m, Code Generating, LLM Explorer Score: 0.08.

Codegen Dataset:trivia qa En Endpoints compatible Gpt bigcode Pytorch Region:us Rlhf Safetensors Sharded Tensorflow Trl

Model Card on HF 🤗: https://huggingface.co/vwxyzjn/starcoderbase-triviaqa

Starcoderbase Triviaqa Parameters and Internals

Model Type

transformers, reinforcement learning

Use Cases

Areas:

Research, Commercial Applications

Limitations:

May generate incorrect or misleading answers, May copy answers from the training data verbatim, May generate language that is hateful or discriminatory, May generate offensive language

Considerations:

Answers should be validated through external sources.

Supported Languages

en (English)

Training Details

Data Sources:

TriviaQA

Methodology:

Fine-tuned using reinforcement learning via TRL's `TextEnvironment`.

Responsible Ai Considerations

Mitigation Strategies:

Disparities between the data contributors and users should inform developers in assessing appropriate use cases. Further research is needed to attribute model generations to sources in the training data.

LLM Name	Starcoderbase Triviaqa
Repository 🤗	https://huggingface.co/vwxyzjn/starcoderbase-triviaqa
Model Size	15.5b
Required VRAM	62.1 GB
Updated	2026-08-02
Maintainer	vwxyzjn
Model Type	gpt_bigcode
Model Files	9.9 GB: 1-of-7 9.9 GB: 2-of-7 9.8 GB: 3-of-7 9.9 GB: 4-of-7 9.8 GB: 5-of-7 9.9 GB: 6-of-7 2.9 GB: 7-of-7
Supported Languages	en
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	bigscience-openrail-m
Transformers Version	4.30.2
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	float32
Activation Function	gelu

Rank the Starcoderbase Triviaqa 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 Starcoderbase Triviaqa

Best Alternatives	Context / RAM	Downloads	Likes
Starchat Alpha	0K / 31.2 GB	548	231
Starchat Beta	0K / 31.2 GB	423	263
...der15B Personal Copilot Merged	0K / 30.9 GB	0	1
Octocoder	0K / 62.1 GB	193	70
...der15B Personal Copilot Merged	0K / 31.2 GB	9	3

Note: green Score (e.g. "73.2") means that the model is better than vwxyzjn/starcoderbase-triviaqa.