| Name | Version | Summary | date |
| llm-bench |
0.4.19 |
Forked off of LLM Benchmark for Throughputs via Ollama |
2024-05-15 10:08:30 |
| ai-edge-torch-nightly |
0.1.dev202405131930 |
Supporting PyTorch models with the Google AI Edge TFLite runtime. |
2024-05-14 02:32:01 |
| pyllms |
0.5.1 |
Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google Palm2/Vertex, Mistral, Ollama, AI21, Cohere, Aleph-Alpha, HuggingfaceHub), with a built-in model performance benchmark. |
2024-05-13 18:29:01 |
| ai-edge-torch |
0.1.0 |
Enables preparing PyTorch models for performant on-device execution. |
2024-05-13 17:45:37 |
| TokenProbs |
1.0.1 |
Extract token-level probabilities from LLMs for classification-type outputs. |
2024-05-08 14:26:33 |
| llmlingua-promptflow |
0.0.1 |
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss. |
2024-05-08 06:38:21 |
| datadreamer.dev |
0.35.0 |
Prompt. Generate Synthetic Data. Train & Align Models. |
2024-05-02 05:36:30 |
| llm-benchmark |
0.3.18 |
LLM Benchmark for Throughputs via Ollama |
2024-05-01 07:49:32 |
| quotientai |
0.0.4 |
CLI for evaluating large language models with Quotient |
2024-04-30 18:46:22 |
| cognitrix |
0.2.3 |
Package for creating AI Agents using llms |
2024-04-29 12:53:36 |
| openai-cost-logger |
0.3.1 |
OpenAI Cost Logger |
2024-04-27 13:48:24 |
| llmlingua |
0.2.2 |
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss. |
2024-04-09 08:21:56 |
| jailbreakbench |
0.1.3 |
An Open Robustness Benchmark for Jailbreaking Language Models |
2024-04-06 15:41:26 |
| peanutbutter |
0.1.1 |
Property-Based Testing and LLMS, what could go wrong? |
2024-04-05 00:26:29 |
| GenCasting |
0.0.8 |
Extract token-level probabilities from LLMs for classification-type outputs. |
2024-04-01 23:13:50 |
| llm_benchmark |
0.3.1 |
LLM Benchmark for Throughputs via Ollama |
2024-03-30 21:47:35 |
| os-copilot |
0.1.0 |
An self-improving embodied conversational agents seamlessly integrated into the operating system to automate our daily tasks. |
2024-03-26 03:25:47 |