jukofyork / transplant-vocabLinks
Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.
☆47Updated last month
Alternatives and similar repositories for transplant-vocab
Users that are interested in transplant-vocab are comparing it to the libraries listed below
Sorting:
- Easily view and modify JSON datasets for large language models☆84Updated 6 months ago
- ☆108Updated 3 months ago
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…☆84Updated last week
- Sparse Inferencing for transformer based LLMs☆215Updated 4 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆97Updated 7 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆63Updated 10 months ago
- ☆68Updated last year
- ☆134Updated 7 months ago
- ☆24Updated 10 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆54Updated 10 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆108Updated last year
- A pipeline parallel training script for LLMs.☆164Updated 7 months ago
- Adding a multi-text multi-speaker script (diffe) that is based on a script from asiff00 on issue 61 for Sesame: A Conversational Speech G…☆25Updated 8 months ago
- cli tool to quantize gguf, gptq, awq, hqq and exl2 models☆76Updated 11 months ago
- ☆62Updated 5 months ago
- REAP: Router-weighted Expert Activation Pruning for SMoE compression☆136Updated last week
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆99Updated 5 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆86Updated last year
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆103Updated 6 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆179Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆148Updated 9 months ago
- entropix style sampling + GUI☆27Updated last year
- SLOP Detector and analyzer based on dictionary for shareGPT JSON and text☆79Updated this week
- automatically quant GGUF models☆219Updated last month
- ☆158Updated 7 months ago
- Lightweight continuous batching OpenAI compatibility using HuggingFace Transformers include T5 and Whisper.☆29Updated 8 months ago
- ☆136Updated last year
- 1.58-bit LLaMa model☆83Updated last year
- Distributed Inference for mlx LLm☆99Updated last year
- Serving LLMs in the HF-Transformers format via a PyFlask API☆71Updated last year