Pinned Loading

1. ollama ollama Public

   Forked from ollama/ollama

   Get up and running with Llama 3, Mistral, Gemma, and other large language models.

   Go

2. paper-rag paper-rag Public

   Daily arxiv's paper searcher using danswer's RAG.

   Python 1 1

3. tensorrtllm_backend_tutorial tensorrtllm_backend_tutorial Public

   Forked from triton-inference-server/tensorrtllm_backend

   The Triton TensorRT-LLM Backend

   Python

4. universal-llm-trainer universal-llm-trainer Public

   Universal LLM Trainer including LoRA, QLoRA, deepspeed, etc.

   Python 1

5. text-embedding-space-GAN text-embedding-space-GAN Public

   Random text synthesis model training code. This model called TESGAN, which is trained via unsupervised way like GAN.

   Python 3

6. deepseek-r1-local-serving deepseek-r1-local-serving Public

   Here, we provide a comprehensive guide on serving the 671B DeepSeek-R1 model on a local GPU setup from start to finish. All you need are 2 A100 GPUs to get started.

   Dockerfile 2