{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"SqueezeLLM","owner":"SqueezeAILab","isFork":false,"description":"[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization","topicNames":["natural-language-processing","text-generation","transformer","llama","quantization","model-compression","efficient-inference","post-training-quantization","large-language-models","llm"],"topicsNotShown":2,"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":0,"issueCount":11,"starsCount":575,"forksCount":37,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-02T03:52:01.121Z"}},{"type":"Public","name":"KVQuant","owner":"SqueezeAILab","isFork":false,"description":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","topicNames":["natural-language-processing","compression","text-generation","transformer","llama","quantization","mistral","model-compression","efficient-inference","efficient-model"],"topicsNotShown":5,"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":7,"starsCount":205,"forksCount":15,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-19T22:28:32.909Z"}},{"type":"Public","name":"LLMCompiler","owner":"SqueezeAILab","isFork":false,"description":"[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling","topicNames":["nlp","natural-language-processing","transformer","llama","efficient-inference","large-language-models","llm","llms","llm-agent","function-calling"],"topicsNotShown":4,"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":1,"starsCount":1107,"forksCount":82,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-15T01:09:39.592Z"}},{"type":"Public","name":"LLM2LLM","owner":"SqueezeAILab","isFork":false,"description":"[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","topicNames":["nlp","natural-language-processing","transformer","llama","data-augmentation","synthetic-dataset-generation","llm","llms","llama2"],"topicsNotShown":0,"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":112,"forksCount":8,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-25T05:33:34.832Z"}}],"repositoryCount":4,"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":"Repositories"}