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.
☆167Updated 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
- A Collection of Pydantic Models to Abstract IRL☆17Updated this week
- Full finetuning of large language models without large memory requirements☆93Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆31Updated 2 weeks ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆137Updated last month
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 10 months ago
- ☆80Updated 2 months ago
- ☆92Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆229Updated last month
- Draw more samples☆186Updated 8 months ago
- ☆97Updated 5 months ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆224Updated 10 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆233Updated 9 months ago
- The history files when recording human interaction while solving ARC tasks☆97Updated last week
- smolLM with Entropix sampler on pytorch☆150Updated 4 months ago
- ☆111Updated 3 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Erasing concepts from neural representations with provable guarantees☆226Updated last month
- This repository explains and provides examples for "concept anchoring" in GPT4.☆72Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated 7 months ago
- smol models are fun too☆89Updated 4 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆168Updated 2 months ago
- Retro styled terminal shell☆26Updated 10 months ago
- Simple Transformer in Jax☆136Updated 8 months ago
- Code repository for the c-BTM paper☆106Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated 10 months ago
- ☆104Updated 2 months ago
- inference code for mixtral-8x7b-32kseqlen☆99Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆77Updated 11 months ago