Silver267 / pytorch-to-safetensor-converter
A simple converter which converts pytorch bin files to safetensor, intended to be used for LLM conversion.
☆54Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for pytorch-to-safetensor-converter
- A high-throughput and memory-efficient inference and serving engine for LLMs☆130Updated 5 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆100Updated 6 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆112Updated last year
- 8-bit CUDA functions for PyTorch in Windows 10☆71Updated last year
- A pipeline parallel training script for LLMs.☆83Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 7 months ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆97Updated last year
- Merge Transformers language models by use of gradient parameters.☆201Updated 3 months ago
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆144Updated 9 months ago
- Low-Rank adapter extraction for fine-tuned transformers model☆162Updated 6 months ago
- Efficient 3bit/4bit quantization of LLaMA models☆19Updated last year
- ☆79Updated last year
- Implementation of DoRA☆283Updated 5 months ago
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- FuseAI Project☆76Updated 3 months ago
- automatically quant GGUF models☆140Updated this week
- Text WebUI extension to add clever Notebooks to Chat mode☆133Updated 10 months ago
- Convenient wrapper for fine-tuning and inference of Large Language Models (LLMs) with several quantization techniques (GTPQ, bitsandbytes…☆145Updated last year
- Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.☆128Updated this week
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆196Updated 7 months ago
- Train llama with lora on one 4090 and merge weight of lora to work as stanford alpaca.☆50Updated last year
- The homepage of OneBit model quantization framework.☆157Updated 4 months ago
- 4 bits quantization of LLaMa using GPTQ☆130Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 5 months ago
- Open Source WizardCoder Dataset☆153Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- Implements harmful/harmless refusal removal using pure HF Transformers☆26Updated 5 months ago
- Synthetic Role-Play Conversation Dataset Generation☆40Updated last year
- LLaMa Tuning with Stanford Alpaca Dataset using Deepspeed and Transformers☆50Updated last year
- A bagel, with everything.☆313Updated 7 months ago