JD-P / minihf
MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.
☆171Updated this week
Alternatives and similar repositories for minihf:
Users that are interested in minihf are comparing it to the libraries listed below
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 2 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆173Updated last year
- A Collection of Pydantic Models to Abstract IRL☆18Updated 2 weeks ago
- ☆109Updated 4 months ago
- Full finetuning of large language models without large memory requirements☆94Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆237Updated 11 months ago
- ☆48Updated last year
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆223Updated last year
- smol models are fun too☆92Updated 5 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 9 months ago
- look how they massacred my boy☆63Updated 6 months ago
- ☆80Updated 4 months ago
- smolLM with Entropix sampler on pytorch☆151Updated 6 months ago
- Long context evaluation for large language models☆206Updated 2 months ago
- ☆92Updated last year
- This repository explains and provides examples for "concept anchoring" in GPT4.☆72Updated last year
- ☆73Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- ☆117Updated last month
- ☆129Updated 8 months ago
- ☆97Updated 6 months ago
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 3 months ago
- The history files when recording human interaction while solving ARC tasks☆108Updated last week
- ☆61Updated last year
- Draw more samples☆189Updated 10 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- Train your own SOTA deductive reasoning model☆91Updated 2 months ago
- ☆112Updated 4 months ago