TypeScript framework for fine-tuning
nodejs javascript typescript ai gpu nextjs ml developer-tools lora fine-tuning mlops llm open-weight-models
-
Updated
Jun 12, 2026 - TypeScript
#
open-weight-models
Here are 17 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Curated list of open-weight AI models with commercially exploitable licenses, verified benchmarks, and no EU restrictions.
-
Updated
Jun 4, 2026
"A clean, from-scratch implementation of the OLMo architecture with KV caching, RoPE, and an efficient autoregressive inference pipeline. Designed as a minimal yet extensible foundation for post-training research, including RLHF, preference optimization, and reasoning-focused systems."
-
Updated
Apr 15, 2026 - Jupyter Notebook
Benchmarking open-weight LLM coding agents as SCOUT delegates: model comparison experiments with pre-registered protocols, blind scoring, and full data.
benchmarking scout goose ai-agents model-comparison supplementary-materials llm-evaluation open-weight-models
-
Updated
Apr 22, 2026 - Python
Tamper Attack Resistance (BlueDot Impact Technical AI Safety Project)
-
Updated
Jun 11, 2026 - Python
Experimental framework for cross-subtask malicious intent detection in stateless AI agents — research into open-weight model safety
cybersecurity ai-safety misinformation llm llm-safety agentic-ai open-weight-models multi-step-tasks
-
Updated
Apr 27, 2026 - Python
Klepon: Taste of Indonesia
-
Updated
May 16, 2026 - Swift
This project implements a complete research pipeline for detecting shortcut-driven reasoning in open-weight language models. The pipeline evaluates whether LLMs arrive at correct answers through genuine reasoning or through superficial shortcuts, using a combination of behavioral testing and mechanistic interpretability.
-
Updated
May 31, 2026 - Python
Time‐Shift LLM Integrity Tester
ai-security backdoor-detection llm-security llm-evaluation model-integrity adversarial-testing open-weight-models
-
Updated
Dec 5, 2025 - Python
Experimental local-first AI workspace powered by local LLMs.
-
Updated
May 12, 2026 - TypeScript
Closing the Opus Gap: Systematic Optimization of Tool-Calling in Open-Weight LLMs on Wafer-Scale Hardware
-
Updated
May 11, 2026
Team DU (Durham University) systems for COLIEE 2026, the Competition on Legal Information Extraction and Entailment, co-located with ICAIL 2026 in Singapore.
learning-to-rank textual-entailment durham-university coliee legal-nlp legal-judgment-prediction llm-ensemble legal-information-retrieval open-weight-models icail coliee-2026 statute-entailment legal-case-retrieval icail-2026
-
Updated
Jun 6, 2026 - Python
Com la tokenització fractura la morfologia catalana i si una segmentació conscient dels morfemes recupera la geometria. Provat en 3 llengües indoeuropees (català, castellà, anglès): el català es fragmenta ×ばつ més que l'anglès; forçar el tall morfèmic recupera la composicionalitat (robust a portadora i replicat en castellà).
nlp morphology catalan gemma tokenization subword salamandra llm qwen low-resource-language representation-geometry open-weight-models
-
Updated
May 28, 2026 - Python
The network where autonomous agents compete to make small open-weight models better — verified, not self-reported. Built on Base. codepit.fun
-
Updated
May 31, 2026 - Python
Anthropic-style emotion-vector geometry, on any open-weight LLM, in one command. Frozen corpus + unified pipeline + statistical rigor + 5-model reference results.
benchmark emotion probe transformer llama mps mistral interpretability sparse-autoencoder apple-silicon llm mechanistic-interpretability anthropic qwen representation-engineering activation-steering open-weight-models
-
Updated
May 8, 2026 - Python
MacOS Electron Client for LLMs that run locally and on the Cloud using LM Studio/Ollama/OpenRouter/Nvidia Build
-
Updated
Jun 7, 2026 - TypeScript
Improve this page
Add a description, image, and links to the open-weight-models topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the open-weight-models topic, visit your repo's landing page and select "manage topics."