{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"SqueezeLLM","owner":"SqueezeAILab","isFork":false,"description":"[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization","allTopics":["natural-language-processing","text-generation","transformer","llama","quantization","model-compression","efficient-inference","post-training-quantization","large-language-models","llm","small-models","localllm"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":15,"starsCount":617,"forksCount":40,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-17T16:52:08.806Z"}},{"type":"Public","name":"LLMCompiler","owner":"SqueezeAILab","isFork":false,"description":"[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling","allTopics":["nlp","natural-language-processing","transformer","llama","efficient-inference","large-language-models","llm","llms","llm-agent","function-calling","llama2","llm-framework","llm-agents","parallel-function-call"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":1308,"forksCount":97,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-10T04:39:34.842Z"}},{"type":"Public","name":"KVQuant","owner":"SqueezeAILab","isFork":false,"description":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","allTopics":["natural-language-processing","compression","text-generation","transformer","llama","quantization","mistral","model-compression","efficient-inference","efficient-model","large-language-models","llm","small-models","localllm","localllama"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":8,"starsCount":249,"forksCount":19,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-10T03:33:51.909Z"}},{"type":"Public","name":"TinyAgent","owner":"SqueezeAILab","isFork":false,"description":"TinyAgent: Function Calling at the Edge!","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":76,"forksCount":14,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-30T06:01:17.010Z"}},{"type":"Public","name":"LLM2LLM","owner":"SqueezeAILab","isFork":false,"description":"[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","allTopics":["nlp","natural-language-processing","transformer","llama","data-augmentation","synthetic-dataset-generation","llm","llms","llama2"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":135,"forksCount":9,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-25T05:33:34.832Z"}},{"type":"Public","name":"open_source_projects","owner":"SqueezeAILab","isFork":false,"description":"Open Source Projects from Pallas Lab","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":16,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-10-10T07:21:11.227Z"}}],"repositoryCount":6,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"SqueezeAILab repositories"}