CohleM / lilLMLinks
A little(lil) Language Model (LM). A tiny reproduction of LLaMA 3's model architecture.
☆54Updated 3 months ago
Alternatives and similar repositories for lilLM
Users that are interested in lilLM are comparing it to the libraries listed below
Sorting:
- AI management tool☆118Updated 9 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆63Updated 6 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆199Updated last year
- ☆134Updated last year
- A compact LLM pretrained in 9 days by using high quality data☆322Updated 4 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆175Updated last year
- Video+code lecture on building nanoGPT from scratch☆69Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago
- Train your own small bitnet model☆75Updated 10 months ago
- ☆95Updated 8 months ago
- 1.58-bit LLaMa model☆82Updated last year
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆184Updated last year
- ☆134Updated 3 months ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆243Updated last year
- The simplest, fastest repository for training/finetuning medium-sized xLSTMs.☆41Updated last year
- ☆133Updated last week
- Guaranteed Structured Output from any Language Model via Hierarchical State Machines☆145Updated 2 months ago
- ☆97Updated 2 months ago
- 1.58 Bit LLM on Apple Silicon using MLX☆221Updated last year
- ☆50Updated 6 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 10 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- A fast batching API to serve LLM models☆185Updated last year
- A pipeline parallel training script for LLMs.☆153Updated 3 months ago
- ☆314Updated 3 weeks ago
- Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget☆157Updated last week
- Easily view and modify JSON datasets for large language models☆81Updated 3 months ago
- ☆118Updated 11 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated 9 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 5 months ago