Pinned Repositories
basedUX
minimal dataset conisting og 363 Human & Assitant dialogs
bitnet
ccpem-modified
A modified dataset consisting of English dialogs between a user and an assistant discussing movie preferences in natural language.
fusedbun
gadit
math lib
llama2-7b-guanaco
Finetune llama2-7b-guanaco
minhash_exp
Deduplication : minhash w/ LSH
notebooks
Obsidian
Maybe the new state of the art vision model? we'll see 🤷♂️
quantize_ggml
Quantize Llama models with ggml and llama.cpp
aloobun's Repositories
aloobun/fusedbun
aloobun/llama2-7b-guanaco
Finetune llama2-7b-guanaco
aloobun/quantize_ggml
Quantize Llama models with ggml and llama.cpp
aloobun/basedUX
minimal dataset conisting og 363 Human & Assitant dialogs
aloobun/bitnet
aloobun/ccpem-modified
A modified dataset consisting of English dialogs between a user and an assistant discussing movie preferences in natural language.
aloobun/cpcd-modified
Conversational Playlist Curation Dataset
aloobun/gadit
math lib
aloobun/llama2-7b-openhermes-15k
A 4-bit qlora refinement of llama-v2-guanaco, fine tuned on the 15k rows of Hermes dataset.
aloobun/minhash_exp
Deduplication : minhash w/ LSH
aloobun/notebooks
aloobun/Obsidian
Maybe the new state of the art vision model? we'll see 🤷♂️
aloobun/train_chosen_one
wip
aloobun/gym-pusht
A gym environment for PushT
aloobun/IN-L3-Tokenizer
aloobun/nvim-replit
An experiment with replit ggml model. Do no use this it's stupid/
aloobun/Pytorch-Optimizers
Different Optimizers available implemented in pytorch
aloobun/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
aloobun/Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
aloobun/remask
aloobun/reward_model_gpt2_tiny
aloobun/SlimTrainer
Full finetuning of large language models without large memory requirements
aloobun/SpeculativeSampling
Accelerating Large Language Model Decoding with Speculative Sampling
aloobun/tinybench
tinybench
aloobun/trinity
aloobun/udlbook_nbs