microsoft / Llama-2-OnnxLinks
☆1,027Updated last year
Alternatives and similar repositories for Llama-2-Onnx
Users that are interested in Llama-2-Onnx are comparing it to the libraries listed below
Sorting:
- C++ implementation for BLOOM☆808Updated 2 years ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,165Updated 11 months ago
- Finetuning Large Language Models on One Consumer GPU in 2 Bits☆731Updated last year
- C++ implementation for 💫StarCoder☆457Updated 2 years ago
- ggml implementation of BERT☆493Updated last year
- Llama 2 Everywhere (L2E)☆1,524Updated last month
- Scale LLM Engine public repository☆813Updated last week
- Python bindings for the Transformer models implemented in C/C++ using GGML library.☆1,878Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,093Updated last year
- ☆547Updated 9 months ago
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,547Updated 6 months ago
- Run inference on MPT-30B using CPU☆575Updated 2 years ago
- Inference Llama 2 in one file of pure 🔥☆2,118Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆52Updated 2 years ago
- ☆1,004Updated 8 months ago
- Salesforce open-source LLMs with 8k sequence length.☆723Updated 8 months ago
- Quantized inference code for LLaMA models☆1,049Updated 2 years ago
- RayLLM - LLMs on Ray (Archived). Read README for more info.☆1,265Updated 6 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆703Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆720Updated last year
- MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs☆928Updated 2 years ago
- ☆470Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,192Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,063Updated 3 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆717Updated last year
- ☆866Updated last year
- ☆1,493Updated 2 years ago
- Finetune llama2-70b and codellama on MacBook Air without quantization☆448Updated last year
- Inference code for Persimmon-8B☆414Updated 2 years ago
- Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)☆568Updated 2 years ago