JD-P / minihfLinks
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.
☆183Updated 2 months ago
Alternatives and similar repositories for minihf
Users that are interested in minihf are comparing it to the libraries listed below
Sorting:
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago
- Full finetuning of large language models without large memory requirements☆94Updated 3 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated this week
- A Collection of Pydantic Models to Abstract IRL☆36Updated last month
- smolLM with Entropix sampler on pytorch☆149Updated last year
- ☆125Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Simple Transformer in Jax☆140Updated last year
- ☆45Updated 2 years ago
- Official repo for Learning to Reason for Long-Form Story Generation☆73Updated 8 months ago
- smol models are fun too☆93Updated last year
- ☆137Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- Draw more samples☆198Updated last year
- ☆50Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated 2 years ago
- ☆94Updated 2 years ago
- An introduction to LLM Sampling☆79Updated last year
- ☆22Updated 2 years ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 7 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 3 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆264Updated this week
- ☆62Updated 2 years ago
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- look how they massacred my boy☆63Updated last year
- Erasing concepts from neural representations with provable guarantees☆242Updated 11 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆233Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- inference code for mixtral-8x7b-32kseqlen☆105Updated 2 years ago
- Extract full next-token probabilities via language model APIs☆248Updated last year