What are the hardware requirements for Phantasor V0.3 137M?

Phantasor V0.3 137M requires approximately 0.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phantasor V0.3 137M and how large is it?

Phantasor V0.3 137M is developed by XeTute, a model with 137m 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 Phantasor V0.3 137M?

Phantasor V0.3 137M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phantasor V0.3 137M by XeTute — VRAM 0.5GB

Name: Phantasor V0.3 137M
Author: XeTute

Phantasor V0.3 137M is an open-source language model by XeTute. Features: 137m LLM, VRAM: 0.5GB, License: mit, LLM Explorer Score: 0.16.

Autotrain compatible Base model:finetune:xetute/pha... Base model:xetute/phantasor v0... Chinese Conversational Dataset:chamoda/atlas-storytel... Dataset:jaydenccc/ai storytell... Dataset:matanp/emotion mapped ... Dataset:xetute/sstory-gen-en z... Dataset:zxbsmk/webnovel cn En Endpoints compatible English Full Generated from trainer Gpt2 Llama-factory Region:us Safetensors Story Tiny Zh

Model Card on HF 🤗: https://huggingface.co/XeTute/Phantasor_V0.3-137M

Phantasor V0.3 137M Parameters and Internals

LLM Name	Phantasor V0.3 137M
Repository 🤗	https://huggingface.co/XeTute/Phantasor_V0.3-137M
Base Model(s)	XeTute/Phantasor_V0.2-137M XeTute/Phantasor_V0.2-137M
Model Size	137m
Required VRAM	0.5 GB
Updated	2025-03-05
Maintainer	XeTute
Model Type	gpt2
Model Files	0.5 GB 0.0 GB
Supported Languages	zh en
Model Architecture	GPT2LMHeadModel
License	mit
Model Max Length	1024
Transformers Version	4.48.2
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	50257
Torch Data Type	float32
Activation Function	gelu_new

Rank the Phantasor V0.3 137M 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 Phantasor V0.3 137M

Best Alternatives	Context / RAM	Downloads	Likes
Gpt2	0K / 0.5 GB	13649095	3385
Gpt2	0K / 0.5 GB	187	1
Gpt2023	0K / 0.3 GB	162	18
GPT2 137M Reasoner V1.0	0K / 0.5 GB	9	1
Phantasor 137M	0K / 0.5 GB	211	1
Phantasor V0.1 137M	0K / 0.5 GB	93	1
Phantasor V0.2 137M	0K / 0.5 GB	73	1
Gpt2 Auth	0K / 0.5 GB	69	0
My GPT2	0K / 0.5 GB	71	0
Xuanxuan	0K / 0.3 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than XeTute/Phantasor_V0.3-137M.