What are the hardware requirements for ShareCaptioner Video?

ShareCaptioner Video requires approximately 17.2 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed ShareCaptioner Video and how large is it?

ShareCaptioner Video is developed by Lin-Chen. 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 ShareCaptioner Video?

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

ShareCaptioner Video by Lin-Chen — VRAM 17.2GB, 32K context

Name: ShareCaptioner Video
Author: Lin-Chen

ShareCaptioner Video is an open-source language model by Lin-Chen. Features: LLM, VRAM: 17.2GB, Context: 32K, LLM Explorer Score: 0.13.

Arxiv:2406.04325 Conversational Custom code Dataset:sharegpt4video/sharegp... Internlmxcomposer2 Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Lin-Chen/ShareCaptioner-Video

ShareCaptioner Video Parameters and Internals

Model Type

video captioning, natural language processing

Use Cases

Areas:

research, hobbyist projects

Primary Use Cases:

high-quality video captioning

Training Details

Data Sources:

ShareGPT4Video dataset, GPT4V-assisted

Data Volume:

120K data instances (40K video-caption pairs, 40K captioning conversations, 40K prompt-to-caption data)

Methodology:

Fine-tuning on GPT4V-assisted data

Model Architecture:

InternLM-Xcomposer2-4KHD

LLM Name	ShareCaptioner Video
Repository 🤗	https://huggingface.co/Lin-Chen/ShareCaptioner-Video
Required VRAM	17.2 GB
Updated	2026-08-06
Maintainer	Lin-Chen
Model Type	internlmxcomposer2
Model Files	10.0 GB: 1-of-2 7.2 GB: 2-of-2 0.0 GB
Model Architecture	InternLM2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.33.1
Is Biased	0
Tokenizer Class	InternLM2Tokenizer
Padding Token	</s>
Vocabulary Size	92544
Torch Data Type	bfloat16

Rank the ShareCaptioner Video 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 ShareCaptioner Video

Best Alternatives	Context / RAM	Downloads	Likes
Songcomposer Sft	32K / 16.7 GB	68	16
Songcomposer Pretrain	32K / 16.7 GB	26	5
MMedLM2	32K / 30.9 GB	12	12
Internlm2 5 Step Prover	8K / 15.4 GB	488	5
Internlm2 Step Prover	8K / 15.4 GB	36	23

Note: green Score (e.g. "73.2") means that the model is better than Lin-Chen/ShareCaptioner-Video.