Article
Multimodal Embedding & Reranker Models with Sentence Transformers
•
22
Stefano Fiorucci PRO
anakin87
AI & ML interests
Language Models: orchestration, post-training, GRPO, synthetic data...
Contributing to Haystack LLM framework 🏗️
Recent Activity
upvoted an article about 11 hours ago
Multimodal Embedding & Reranker Models with Sentence Transformers reacted to theirpost with 🔥 about 12 hours ago
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: https://huggingface.co/spaces/anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe reacted to theirpost with ❤️ 1 day ago
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: https://huggingface.co/spaces/anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toeOrganizations
upvoted an article about 11 hours ago
reactedto their post with 🔥 about 12 hours ago
Post
2324
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
reactedto their post with ❤️ 1 day ago
Post
2324
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
liked a
Space 1 day ago
upvoted a collection 1 day ago
posted an update 1 day ago
Post
2324
📣 I just published a free course on Reinforcement Learning Environments for Language Models!
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
📌 COURSE: https://github.com/anakin87/llm-rl-environments-lil-course
Over the past year, we've seen a shift in LLM Post-Training.
Previously, Supervised Fine-Tuning was the most important part: making models imitate curated Question-Answer pairs.
Now we also have Reinforcement Learning with Verifiable Rewards. With techniques like GRPO, models can learn through trial and error in dynamic environments. They can climb to new heights without relying on expensively prepared data.
But what actually are these environments in practice❓ And how do you build them effectively❓
Fascinated by these concepts, I spent time exploring this space through experiments, post-training Small Language Models.
I've packaged everything I learned into this short course.
What you'll learn
🔹 Agents, Environments, and LLMs: how to map Reinforcement Learning concepts to the LLM domain
🔹 How to use Verifiers (open-source library by Prime Intellect) to build RL environments as software artifacts
🔹 Common patterns: How to build single-turn, multi-turn, and tool-use environments
🔹 Hands-on: turn a small language model (LFM2-2.6B by LiquidAI) into a Tic Tac Toe master
🔸 Build the game Environment
🔸 Use it to generate synthetic data for SFT warm-up
🔸 Group-based Reinforcement Learning
If you're interested in building "little worlds" where LLMs can learn, this course is for you.
---
🤗🕹️ Play against the trained model: anakin87/LFM2-2.6B-mr-tictactoe
📚 HF collection (datasets + models): https://huggingface.co/collections/anakin87/lfm2-26b-mr-tic-tac-toe
reactedto RakshitAralimatti's post with 👍 1 day ago
Post
706
🔥 GLM-5.1 (zai-org/GLM-5.1) — Quietly One of the Best flagship model for agentic engineering and Coding tasks Right Now
threw some LangGraph agent code at it, a messy RAG pipeline, some async Python stuff and it just handled it. no drama, no hallucinated methods, actually usable output on the first try.
open source closing the gap this fast is genuinely exciting. go check zai-org/GLM-5.1 on HF if you haven't already
Good work @zai-org-3
threw some LangGraph agent code at it, a messy RAG pipeline, some async Python stuff and it just handled it. no drama, no hallucinated methods, actually usable output on the first try.
open source closing the gap this fast is genuinely exciting. go check zai-org/GLM-5.1 on HF if you haven't already
Good work @zai-org-3
- 1 reply
updated a
Space 1 day ago
published a
Space 1 day ago
liked a
model 4 days ago
updated 5
models 5 days ago
anakin87/LFM2-2.6B-mr-tictactoe
Text Generation • 3B • Updated • 279
anakin87/LFM2-2.6B-ttt-rl-2
Text Generation • Updated • 9
anakin87/LFM2-2.6B-ttt-rl-merged
Text Generation • 3B • Updated • 11
anakin87/LFM2-2.6B-ttt-rl
Text Generation • Updated
anakin87/LFM2-2.6B-ttt-sft
Text Generation • 3B • Updated • 8
updated 2
datasets 5 days ago
updated a
collection 5 days ago