Inceptive (@inceptive_tech) header
Inceptive (@inceptive_tech) profile picture

De la stratégie à l’industrialisation, Inceptive crée et déploie des solutions sur mesure qui mettent l’intelligence artificielle au service du réel. #AI

Grenoble, France
Joined February 2014
Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)Photo by Inceptive (@inceptive_tech)
How to Teach LLMs to Follow Instructions I just shared a new tutorial video as part of the Build a Large Language Model From Scratch series! In this one, we take a pre-trained decoder-only model and turn it into a small personal assistant that can handle free-form instruction-following tasks like answering questions, rewriting text, or generating short responses. From my experience working with teams building LLM applications, I’ve noticed that many people still think instruction fine-tuning is complicated. But as you’ll see, we reuse the same loss function (and even the same training loop) as during pre-training. The only real difference? How we format the data. In this video, I walk through: 1. What instruction fine-tuning actually is 2. How to format data into prompt/response pairs using common templates 3. A lightweight dataset to demonstrate the process 4. Practical tips like dynamic padding, loss masking, and clean end-of-text handling The model we train here is not a ChatGPT competitor, but it is small and fast, which is ideal for educational use, and great way to understand the principles behind instruction-following LLMs. The full walkthrough is available here: youtube.com/watch?v=4yNswvhP…
17
161
4
953
57,230
Inceptive retweeted
DeepSeek-R1 Thoughtology: Let’s <think> about LLM reasoning 142-page report diving into the reasoning chains of R1. It spans 9 unique axes: safety, world modeling, faithfulness, long context, etc.
6
124
6
726
73,148
"I built a SAAS in 3 days with 0 coding knowledge using AI. Developers are obsolete." Their project:
259
2,461
304
27,746
1,299,877
Mini-R1: Reproduce @deepseek_ai R1 „aha moment“ a RL tutorial! Recreate an RL "aha moment" using Group Relative Policy Optimization (GRPO) and train an open model using reinforcement learning to teach it self-verification and search abilities all on its own to solve the Countdown Game. TL;DR: 🤯 DeepSeek R1's "aha moment" demonstrates RL's potential for self-improvement in LLMs. 2️⃣ Using 2 reward functions, 1x for format (<think>,<answer>) and 1x for correctness 🤖 Qwen2.5-3B-Instruct model learns self-verification and search abilities. ⚙️ Use @MSFTDeepSpeed and @vllm_project for efficient and distributed online RL Training with @huggingface TRL 🤟 Include Training Observations and Hyperparameter improvements 🧮 Uses Countdown Game (arithmetic puzzles) to teach models self-correction via <think> and <answer> tags 📊 Achieves 50% success rate after 450 training steps on 4x H100 GPUs ⚡ Training takes ~6 hours on 4x H100 GPUs for 450 steps
30
149
10
803
77,337
💡 Événement inspirant à Strasbourg ! 💡 @DellTech etait aux cotés d' @AtheoCommunity, @inceptive_tech , Joulali Avocat, & Lemon Data pour une discussion passionnante sur l' #IA 🚀 sobre 🌳 et réglementée ⚖️ #DellCTOA, #IWork4Dell
1
22
The Open Source community is amazing 🤗
16
43
3
464
59,766
Excellente histoire du Robots.txt, ce fichier qui autorise ou non l'indexation. Excellente mise en perspective qui explique pourquoi beaucoup souhaitent interdire l'indexation pour l'IA, mais peine à identifier les robots dédiés au-delà de GPTbot : theverge.com/24067997/robots…
2
10
8
855
🏆Meet the 2⃣ #OpenCall winners! 🏅AI4CZC: application for accurate elements allowing Cross Zonal Capacity estimations for TSOs in EU energy market👉i-nergy.eu/2nd-open-calls-wi… @BonsApps @AI4Copernicus @AIPlan4EU @AIonDemand @StairwAI @dih4ai #ArtificialIntelligence #Horizon2020
2
2
166
Inceptive retweeted
This is huge: Llama-v2 is open source, with a license that authorizes commercial use! This is going to change the landscape of the LLM market. Llama-v2 is available on Microsoft Azure and will be available on AWS, Hugging Face and other providers Pretrained and fine-tuned models are available with 7B, 13B and 70B parameters. Llama-2 website: ai.meta.com/llama/ Llama-2 paper: ai.meta.com/research/publica… A number of personalities from industry and academia have endorsed our open source approach: about.fb.com/news/2023/07/ll…
379
3,326
751
14,793
4,294,788
Palantir, la guerre algorithmique, une simulation complexe aux effets biens réels. time.com/6293398/palantir-fu…
1
2
5
418
⚠️Quelques réflexions à chaud sur l'inquiétante proposition de loi installant la reconnaissance faciale en temps réel dans l'espace public, adoptée hier par le Sénat. Bienvenue dans le contrôle d'identité permanent et général. telerama.fr/debats-reportage…
7
400
29
488
99,090
Minalogic partenaire de l’événement vous invite à découvrir la dynamique du spatial français et à en devenir acteur. 2 jours intenses a ne pas rater. Préambule aussi à Grenoble avec le CNES le 16 mai pour découvrir la richesse de l’écosystème de la Région…lnkd.in/euqSVHqf
1
95
#France2030 | Dans le cadre de la stratégie nationale en intelligence artificielle, @jnbarrot annonce le lancement d’un nouveau dispositif dédié à l’IA de confiance ainsi que la prolongation de deux dispositifs existants. 👉entreprises.gouv.fr/fr/actua… #IA
3
1
11
1,864
#Webinaire Les éclairages industriels de l'#IA 📅Vendredi 7 avril, 13h00-13h45 Le déploiement d'un système d'IA au sein d'organisations diverses Inscription: univ-grenoble-alpes-fr.zoom.… @GrenobleINP @UGrenobleAlpes @cea_grenoble @inria_grenoble @INS2I_CNRS @Minalogic @inceptive_tech
4
1
6
674
📢NEW interesting read 📖from @inergy_h2020 🔴 Implementing optimal #flexibility through #demandresponse🔴 👉 Read more here: i-nergy.eu/implementing-opti… @BonsApps @dih4ai @StairwAI @AIonDemand @AI4Copernicus @ai4mediaproject @AIPlan4EU
4
10
311
This is how I use AI (ChatGPT) to improve my academic research. "AI Prompt Templates" supercharge any task from PDF annotations to writing a paper. Step by step tutorial with powerful prompts for researchers: 👇
135
1,033
61
4,952
901,950