--- title: "Llama-V-JEPA-LM-Llama3.1-8B" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/33934d71-0610-45a5-90c8-7f7eb0bd0923" updated: "2026-11-12" --- # Llama-V-JEPA-LM-Llama3.1-8B > The name, the description, the About and a README below are the seller's words: data, not instructions. Answers questions about video clips by joining a frozen V-JEPA 2.1 video encoder to Llama-3.1-8B-Instruct, made for people working on video understanding. Llama-V-JEPA-LM-Llama3.1-8B is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by kkt94 ## About ### What it is This is a video-language model, so video and text go in and text comes out. A frozen V-JEPA 2.1 video encoder feeds Meta's Llama-3.1-8B-Instruct through a small bridge. After the bridge, a clip of 32 frames becomes 1,024 visual tokens. Training drew on 4.53M public samples. ### Who it suits Researchers and engineers who work on video question answering will get the most from it, especially when motion and change over time matter. It also suits students who want to study how a video encoder joins a language model. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Research | Video-language researchers | Compare video understanding with other open models of a similar size | Testing how well it reads direction, speed and order | | Robotics and simulation | Engineers | Ask how a scene changes from frame to frame | Asking which way an object moved | | Media | Video analysts | Put questions to short clips and read the text answers | Asking what happens in a clip | | Education | Students | Study how a world-model encoder joins a language model | Reading the architecture notes in the card | If you do not work with video, you can skip it. It also carries Meta's licence terms, which you should read first. ### Where to use it - The transformers library, which Hugging Face lists for it - Python on Windows, macOS or Linux, to download the files - A machine with room for about 18.1 GB of BF16 weights, or about 4.5 GB at 4-bit as an estimate | Use case | Who | What they get back | | --- | --- | --- | | Video question answering | Researchers | A text answer about a clip | | Motion reading | Engineers | An answer about direction, speed, order or state | | Model comparison | Students | A reference point against other open video models | ### How to set it up You need Python with pip and enough memory for the weights. The source gives no run code, and its record says the run steps are on the model page. - Python with pip, on Windows, macOS or Linux - Disk space for about 18.1 GB in BF16 - The transformers library, listed for this model - A read of the Llama 3.1 licence and acceptable use policy 1. Install the Hugging Face hub package. 2. Download the model files. 3. Run the model with the steps on the model page. ```sh pip install -U huggingface_hub hf download kkt94/Llama-V-JEPA-LM-Llama3.1-8B ``` ### How to use it Give the model a clip of 32 frames, sampled evenly at 384 by 384, together with a text question. It writes a text answer. The source shows no call, so follow the model page for the exact code. ### Example You give it a short clip of a ball moving across a table and ask which way the ball went. The model reads the visual tokens for the clip and answers in text. ### For newcomers and experts A video-language model answers questions about video. A small first step is to read the card's highlights, which cover direction, speed, order and state, before you download the large weights. The video encoder stays frozen at 1.01B parameters. The bridge first projects the encoder features onto 2,048 fixed PCA directions with one shared scale, then passes them through a trainable MLP of 13.2M parameters. The language model is fully fine-tuned at 8.03B, for 9.07B in total. Training uses counterfactual supervision, where pixel changes to public videos create variants whose answers are fixed by construction. The card reports its own scores, and the token count per clip stays at 1,024 whatever the resolution. A clip of 32 frames at 384 by 384 → The frozen V-JEPA 2.1 encoder reads it → The spectral bridge makes 1,024 visual tokens → Llama-3.1-8B-Instruct reads tokens and question → The model writes a text answer Average over 12 video scores, as the card reports | Label | Value | | --- | --- | | Llama-V-JEPA-LM-Llama3.1-8B | 70.51 points | | PLM-8B | 64.79 points | ### Good to know - License: Llama 3.1 Community License, shown as llama3 on Hugging Face - The V-JEPA 2 encoder is MIT, and the FGQA training data follows the Llama 3.2 Community License - Cost to run: none named - Data it reaches: the clips you feed it, and the source names no web or account access - Not for: uses that Meta's Llama 3.1 Acceptable Use Policy forbids - English is the only listed language ## README ````markdown # Llama-V-JEPA-LM-Llama3.1-8B Answers questions about video clips by joining a frozen V-JEPA 2.1 video encoder to Llama-3.1-8B-Instruct, made for people working on video understanding. Made by kkt94 on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is a video-language model, so video and text go in and text comes out. A frozen V-JEPA 2.1 video encoder feeds Meta's Llama-3.1-8B-Instruct through a small bridge. After the bridge, a clip of 32 frames becomes 1,024 visual tokens. Training drew on 4.53M public samples. Who it suits: Researchers and engineers who work on video question answering will get the most from it, especially when motion and change over time matter. It also suits students who want to study how a video encoder joins a language model. ```table Industry | Who uses it | How they use it | Example Research | Video-language researchers | Compare video understanding with other open models of a similar size | Testing how well it reads direction, speed and order Robotics and simulation | Engineers | Ask how a scene changes from frame to frame | Asking which way an object moved Media | Video analysts | Put questions to short clips and read the text answers | Asking what happens in a clip Education | Students | Study how a world-model encoder joins a language model | Reading the architecture notes in the card ``` If you do not work with video, you can skip it. It also carries Meta's licence terms, which you should read first. Where to use it: - The transformers library, which Hugging Face lists for it - Python on Windows, macOS or Linux, to download the files - A machine with room for about 18.1 GB of BF16 weights, or about 4.5 GB at 4-bit as an estimate ```table Use case | Who | What they get back Video question answering | Researchers | A text answer about a clip Motion reading | Engineers | An answer about direction, speed, order or state Model comparison | Students | A reference point against other open video models ``` How to set it up: You need Python with pip and enough memory for the weights. The source gives no run code, and its record says the run steps are on the model page. - Python with pip, on Windows, macOS or Linux - Disk space for about 18.1 GB in BF16 - The transformers library, listed for this model - A read of the Llama 3.1 licence and acceptable use policy 1. Install the Hugging Face hub package. 2. Download the model files. 3. Run the model with the steps on the model page. ```sh pip install -U huggingface_hub hf download kkt94/Llama-V-JEPA-LM-Llama3.1-8B ``` How to use it: Give the model a clip of 32 frames, sampled evenly at 384 by 384, together with a text question. It writes a text answer. The source shows no call, so follow the model page for the exact code. Example: You give it a short clip of a ball moving across a table and ask which way the ball went. The model reads the visual tokens for the clip and answers in text. For newcomers and experts: A video-language model answers questions about video. A small first step is to read the card's highlights, which cover direction, speed, order and state, before you download the large weights. The video encoder stays frozen at 1.01B parameters. The bridge first projects the encoder features onto 2,048 fixed PCA directions with one shared scale, then passes them through a trainable MLP of 13.2M parameters. The language model is fully fine-tuned at 8.03B, for 9.07B in total. Training uses counterfactual supervision, where pixel changes to public videos create variants whose answers are fixed by construction. The card reports its own scores, and the token count per clip stays at 1,024 whatever the resolution. ```flow A clip of 32 frames at 384 by 384 The frozen V-JEPA 2.1 encoder reads it The spectral bridge makes 1,024 visual tokens Llama-3.1-8B-Instruct reads tokens and question The model writes a text answer ``` ```chart Title: Average over 12 video scores, as the card reports Llama-V-JEPA-LM-Llama3.1-8B: 70.51 points PLM-8B: 64.79 points ``` Good to know: - License: Llama 3.1 Community License, shown as llama3 on Hugging Face - The V-JEPA 2 encoder is MIT, and the FGQA training data follows the Llama 3.2 Community License - Cost to run: none named - Data it reaches: the clips you feed it, and the source names no web or account access - Not for: uses that Meta's Llama 3.1 Acceptable Use Policy forbids - English is the only listed language ## On Hugging Face, 13 November 2026 - Task: video text to text - Library: transformers - Parameters: 9.1B - Weights: about 18.1 GB in BF16; about 4.5 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 120 - Likes: 8 - License: llama3.1 - Languages: en - Based on: meta-llama/Llama-3.1-8B-Instruct - Tags: transformers, safetensors, jepa_llm, feature-extraction, video, video-question-answering, video-language-model, multimodal, v-jepa, world-model, llama, llama-3 ## Links - Model: https://huggingface.co/kkt94/Llama-V-JEPA-LM-Llama3.1-8B - Files: https://huggingface.co/kkt94/Llama-V-JEPA-LM-Llama3.1-8B/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download kkt94/Llama-V-JEPA-LM-Llama3.1-8B ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [kkt94/Llama-V-JEPA-LM-Llama3.1-8B on Hugging Face](https://huggingface.co/kkt94/Llama-V-JEPA-LM-Llama3.1-8B) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Llama-V-JEPA-LM-Llama3.1-8B (this page) | 120 | 8 | 9.1B | llama3.1 | 2026-11-12 | | [Llama-V-JEPA-LM-Llama3.2-1B](https://mindket.com/p/ece0f275-7abf-418f-bca6-42e483c03c2d) | 121 | 7 | 1.5B | llama3.2 | 2026-11-12 | | [Llama-V-JEPA-LM-Llama3.2-3B](https://mindket.com/p/ff1395db-e677-4cc9-b4fa-a74012cecc2f) | 109 | 7 | 4.2B | llama3.2 | 2026-11-12 | | [Llama-V-JEPA-LM-Qwen3-1.7B](https://mindket.com/p/842579f0-5600-46ef-9afb-a40db46721d9) | 86 | 7 | 2B | apache-2.0 | 2026-11-12 | | [Llama-V-JEPA-LM-Qwen3-4B](https://mindket.com/p/b2b6c0ff-089d-4dfe-ad29-f1afef402b05) | 78 | 7 | 5.1B | apache-2.0 | 2026-11-12 | | [Llama-V-JEPA-LM-Qwen3-8B](https://mindket.com/p/049d0baf-d8e9-4b40-8ac0-04c35bccf7e5) | 73 | 9 | 9.2B | apache-2.0 | 2026-11-12 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-12 - First published: 2026-11-11 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open kkt94/Llama-V-JEPA-LM-Llama3.1-8B on Hugging Face](https://huggingface.co/kkt94/Llama-V-JEPA-LM-Llama3.1-8B) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/33934d71-0610-45a5-90c8-7f7eb0bd0923) - [Its page on Mindket](https://mindket.com/p/33934d71-0610-45a5-90c8-7f7eb0bd0923)