wozeparrot / tinyrwkvLinks
tinygrad port of the RWKV large language model.
☆45Updated 5 months ago
Alternatives and similar repositories for tinyrwkv
Users that are interested in tinyrwkv are comparing it to the libraries listed below
Sorting:
- Inference of Mamba models in pure C☆191Updated last year
- ☆40Updated 2 years ago
- GGML implementation of BERT model with Python bindings and quantization.☆56Updated last year
- RWKV in nanoGPT style☆192Updated last year
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆73Updated 6 months ago
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆313Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated 10 months ago
- ☆49Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- inference code for mixtral-8x7b-32kseqlen☆101Updated last year
- Experiments with BitNet inference on CPU☆54Updated last year
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated last year
- Full finetuning of large language models without large memory requirements☆94Updated last year
- Framework agnostic python runtime for RWKV models☆146Updated 2 years ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Train your own small bitnet model☆75Updated 10 months ago
- RWKV, in easy to read code☆71Updated 5 months ago
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆41Updated 2 years ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated last year
- Merge Transformers language models by use of gradient parameters.☆207Updated last year
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.☆71Updated 2 years ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- GPT-2 small trained on phi-like data☆67Updated last year
- Embeddings focused small version of Llama NLP model☆104Updated 2 years ago
- Course Project for COMP4471 on RWKV☆17Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- Fast approximate inference on a single GPU with sparsity aware offloading☆38Updated last year
- WebGPU LLM inference tuned by hand☆151Updated 2 years ago
- Tune MPTs☆84Updated 2 years ago