sdan / selfextendLinks
an implementation of Self-Extend, to expand the context window via grouped attention
☆119Updated last year
Alternatives and similar repositories for selfextend
Users that are interested in selfextend are comparing it to the libraries listed below
Sorting:
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Full finetuning of large language models without large memory requirements☆94Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆168Updated last year
- inference code for mixtral-8x7b-32kseqlen☆101Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆175Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆140Updated 5 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated 9 months ago
- ☆47Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- Evaluating LLMs with CommonGen-Lite☆90Updated last year
- ☆157Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆240Updated 5 months ago
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- Merge Transformers language models by use of gradient parameters.☆206Updated 11 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆239Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- ☆134Updated 11 months ago
- Let's create synthetic textbooks together :)☆75Updated last year
- ☆115Updated 7 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆105Updated 7 months ago
- Cerule - A Tiny Mighty Vision Model☆66Updated 10 months ago
- ☆74Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆223Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- ☆87Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 5 months ago
- Simple GRPO scripts and configurations.☆59Updated 5 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- Efficient vector database for hundred millions of embeddings.☆207Updated last year