PicoCreator / RWKV-LM-LoRALinks
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
☆10Updated last year
Alternatives and similar repositories for RWKV-LM-LoRA
Users that are interested in RWKV-LM-LoRA are comparing it to the libraries listed below
Sorting:
- ☆13Updated last year
- ☆27Updated last year
- Modified Beam Search with periodical restart☆12Updated 8 months ago
- Experimental sampler to make LLMs more creative☆31Updated last year
- A large-scale RWKV v6, v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to de…☆35Updated this week
- entropix style sampling + GUI☆26Updated 7 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- Script and instruction how to fine-tune large RWKV model on your data for Alpaca dataset☆31Updated 2 years ago
- Run ONNX RWKV-v4 models with GPU acceleration using DirectML [Windows], or just on CPU [Windows AND Linux]; Limited to 430M model at this…☆20Updated 2 years ago
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆15Updated 6 months ago
- RWKV centralised docs for the community☆25Updated 2 months ago
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆25Updated last year
- ☆34Updated last month
- QLoRA with Enhanced Multi GPU Support☆37Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆40Updated 2 years ago
- 🚀 Automatically convert unstructured data into a high-quality 'textbook' format, optimized for fine-tuning Large Language Models (LLMs)☆25Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated last year
- 基于RWKV模型的角色扮演，实际上是个改的妈都不认识的 RWKV_Role_Playing☆16Updated last year
- BlinkDL's RWKV-v4 running in the browser☆46Updated 2 years ago
- Trying to deconstruct RWKV in understandable terms☆14Updated 2 years ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated 2 years ago
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆42Updated 6 months ago
- Chatbot that answers frequently asked questions in French, English, and Tunisian using the Rasa NLU framework and RWKV-4-Raven☆13Updated 2 years ago
- Merge LLM that are split in to parts☆25Updated last year
- ☆12Updated 2 years ago
- Train Llama Loras Easily☆30Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆32Updated last year
- ☆39Updated 2 years ago