YuvrajSingh-mist / SmolLlamaLinks
So, I trained a Llama a 130M architecture I coded from ground up to build a small instruct model from scratch. Trained on FineWeb dataset form HuggingFace consisting of 15 M texts (10BT snapshot) for a total of full 3 epochs
☆15Updated 2 months ago
Alternatives and similar repositories for SmolLlama
Users that are interested in SmolLlama are comparing it to the libraries listed below
Sorting:
- ☆46Updated 2 months ago
- An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning☆32Updated last month
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆64Updated 7 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆80Updated last month
- rl from zero pretrain, can it be done? we'll see.☆56Updated this week
- Fine tune Gemma 3 on an object detection task☆57Updated this week
- ☆39Updated last month
- A locally trained model of Stoney Nakoda has been developed and released. You can access the working model here or train your own instanc…☆10Updated 2 months ago
- ☆41Updated last month
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆101Updated 3 months ago
- ☆63Updated last month
- Set of scripts to finetune LLMs☆37Updated last year
- ☆47Updated 4 months ago
- Simple GRPO scripts and configurations.☆58Updated 4 months ago
- Fine-tunes a student LLM using teacher feedback for improved reasoning and answer quality. Implements GRPO with teacher-provided evaluati…☆44Updated last month
- ☆74Updated 8 months ago
- look how they massacred my boy☆63Updated 8 months ago
- ☆114Updated 6 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆69Updated last week
- Simple examples using Argilla tools to build AI☆53Updated 7 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆49Updated 11 months ago
- ☆51Updated 7 months ago
- Transformers from scratch using PyTorch & NumPy.☆26Updated 4 months ago
- The simplest, fastest repository for training/finetuning medium-sized xLSTMs.☆41Updated last year
- A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse range of tasks☆36Updated last year
- ☆86Updated 9 months ago
- Lego for GRPO☆28Updated 3 weeks ago
- ☆89Updated 2 months ago
- Cerule - A Tiny Mighty Vision Model☆66Updated 9 months ago