# Evaluating my own model **URL:** \ **Category:** Intermediate\ **Created:** [February 19, 2025, 3:23pm UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827 "2025-02-19T15:23:15Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![sourabhY](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sourabhy/32/40447_2.png) [@sourabhY](https://discuss.huggingface.co/u/sourabhY)\ **Post date:** [February 19, 2025, 3:23pm UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/1 "2025-02-19T15:23:15Z")
I have model which I want to evaluate how and where can i do this . like I want to use some visual ques answering and some math benchmarks also. thanks for help in advance ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 20, 2025, 5:26am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/2 "2025-02-20T05:26:26Z")
Like this? > [@How can I evaluate a fine tuned LLM?](https://discuss.huggingface.co/t/how-can-i-evaluate-a-fine-tuned-llm/134538): > > Hi there! I am curious about how fine tuned large language models are evaluated? I mean, I fine tuned a model for specific task like a question-answer chatbot for my business but how can I decide to my language model is good, bad or terrible? Is there any ways to evaluate fine tuned model such as token similarity, semantic similarity… > **[Let's talk about LLM evaluation](https://huggingface.co/blog/clefourrier/llm-evaluation)** > > A Blog post by Clémentine Fourrier on Hugging Face ---
**Author:** ![sourabhY](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sourabhy/32/40447_2.png) [@sourabhY](https://discuss.huggingface.co/u/sourabhY)\ **Post date:** [February 20, 2025, 5:44am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/3 "2025-02-20T05:44:12Z")
Ohh but how dp people evaluate their models on standard benchmarks like MMLU, docVQA, etc. which we see in model releases and papers. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 20, 2025, 5:51am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/4 "2025-02-20T05:51:33Z")
You could probably run each benchmark individually, but if you’re thinking about comparing it to other models, it might be more reliable and easier to ask the model to evaluate the leaderboard. > **[What's going on with the Open LLM Leaderboard?](https://huggingface.co/blog/open-llm-leaderboard-mmlu)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[open-llm-leaderboard (Open LLM Leaderboard)](https://huggingface.co/open-llm-leaderboard)** > > Evaluating open LLMs ---
**Author:** ![humanxs](https://avatars.discourse-cdn.com/v4/letter/h/f05b48/32.png) [@humanxs](https://discuss.huggingface.co/u/humanxs)\ **Post date:** [February 21, 2025, 9:55am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/5 "2025-02-21T09:55:48Z")
I’m New to [huggingface.co](http://huggingface.co). I know this wrong area where I’m posting this but there’s no one to answer my question, I hope you guys will tolerate me. I’m running facefusion… and had processed a video which is saved in "/tmp " But I don’t know how to access that directory any help? The video was still processing when I logged out of my hugging face account and when I came back in it was showing completed in terminal But I can’t access that processed file. I have posted this question in beginners Category but its been 2 days and its still pending. I don’t know where to move forward. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 21, 2025, 10:16am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/6 "2025-02-21T10:16:09Z")
Here. I don’t understand the situation well. There are multiple Face Fusions… > [@How to access /tmp files](https://discuss.huggingface.co/t/how-to-access-tmp-files/142196): > > I’m running facefusion… and had processed a video which is saved in "/tmp " But I don’t know how to access that directory any help? ---
**Author:** ![rwmasood](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/rwmasood/32/29460_2.png) [@rwmasood](https://discuss.huggingface.co/u/rwmasood)\ **Post date:** [February 21, 2025, 10:25am UTC](https://discuss.huggingface.co/t/evaluating-my-own-model/141827/7 "2025-02-21T10:25:41Z")
try this: > **[GitHub - EleutherAI/lm-evaluation-harness: A framework for few-shot evaluation of language...](https://github.com/EleutherAI/lm-evaluation-harness)** > > A framework for few-shot evaluation of language models.