microsoft/FILM
quality grade D, 43 out of 100Official repo for "Make Your LLM Fully Utilize the Context"
- stars
- 275
- stars gained this week
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Prompt management, templating, DSLs, constrained decoding and guaranteed-schema output.
Signals: prompt-engineering, prompt, prompts, structured-output, json-schema, constrained-decoding, dspy, prompt-management
240 results
Official repo for "Make Your LLM Fully Utilize the Context"
Minimize LLM token complexity to save API costs and model computations.
LLM prompts, llama3 prompts, llama2 prompts
Dead Simple LLM Abliteration
Collection of LLM system prompts
My LLM skills
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
No description
Examples and guides for using the LLMs
I play with my best friend GPT
No description
A semantic collision engine for non-trivial LLM idea generation. Operationalizes Koestler's bisociation theory (1964): injects structurally distant knowledge domains into the prompt, forces collisions, surfaces non-trivial ideas. Empirical validation in CL-ML/open-collider-research.
Jailbreak for ChatGPT: Predict the future, opine on politics and controversial topics, and assess what is true. May help us understand more about LLM Bias
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
基于大语言模型(LLM)和多智能体(Multi-Agent),探究AI写小说能力的边界
Constrained Decoding for LLMs against JSON Schema
Neovim plugin for interacting with LLM's and building editor integrated prompts.
Gemini Prompts, Gemini 3 Prompts, jailbreak, LLM Prompts, LangGPT —— by 云中江树
No description
A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.
No description
Transform developer documentation to clean Markdown
Make any LLM to think like OpenAI o1 and deepseek R1
collections-of-leaked-prompts
24,523 repositories in the index in total.