Pinned Repositories
axolotl
Go ahead and axolotl questions
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
chroma
the AI-native open-source embedding database
evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
GameDevScripts
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
llm
Access large language models from the command-line
LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
4lexanderWatts's Repositories
4lexanderWatts/GameDevScripts
4lexanderWatts/LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
4lexanderWatts/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
4lexanderWatts/axolotl
Go ahead and axolotl questions
4lexanderWatts/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
4lexanderWatts/chroma
the AI-native open-source embedding database
4lexanderWatts/evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
4lexanderWatts/haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
4lexanderWatts/llm
Access large language models from the command-line
4lexanderWatts/nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
4lexanderWatts/ollama
Get up and running with Llama 2, Mistral, and other large language models locally.
4lexanderWatts/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
4lexanderWatts/unsloth
5X faster 60% less memory QLoRA finetuning