Mihaiii / backtrack_sampler
An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
☆105Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for backtrack_sampler
- Low-Rank adapter extraction for fine-tuned transformers model☆162Updated 6 months ago
- ☆92Updated last month
- smolLM with Entropix sampler on pytorch☆137Updated last week
- ☆64Updated 5 months ago
- ☆104Updated 7 months ago
- ☆116Updated 2 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated 10 months ago
- ☆49Updated 7 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆231Updated 5 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆90Updated this week
- Just a bunch of benchmark logs for different LLMs☆114Updated 3 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆201Updated 6 months ago
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆141Updated 9 months ago
- ☆223Updated 3 weeks ago
- code for training & evaluating Contextual Document Embedding models☆93Updated this week
- ☆103Updated 2 months ago
- ☆72Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆221Updated 6 months ago
- ☆74Updated 2 weeks ago
- entropix style sampling + GUI☆25Updated last week
- Let's create synthetic textbooks together :)☆70Updated 9 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆273Updated last month
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆219Updated last week
- Full finetuning of large language models without large memory requirements☆93Updated 10 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆151Updated this week
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆172Updated 3 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- An introduction to LLM Sampling☆61Updated this week
- ☆52Updated 5 months ago
- A pipeline parallel training script for LLMs.☆83Updated this week