Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
-
Updated
Oct 19, 2016 - Lua
#
character-level
Here are 37 public repositories matching this topic...
Code accompanying Incorporating Chinese Characters of Words for Lexical Sememe Prediction (ACL2018) https://arxiv.org/abs/1806.06349
-
Updated
Sep 28, 2018 - Python
Multi lingual character based named entity recognizer
-
Updated
Apr 8, 2018 - Python
Implementation of the Character-level Intra Attention Network (CIAN) for Natural Language Inference (NLI) upon SNLI and MultiNLI corpus
keras attention-mechanism natural-language-inference snli character-level intra-attention repeval mnli multinli
-
Updated
Nov 24, 2017 - Python
a 5M parameter solution to a problem you could solve by counting on your fingers
-
Updated
Apr 11, 2026 - Python
LittleLM: A tiny character-level n-gram language model for local corpus building and collaborative experimentation.
-
Updated
Mar 21, 2026 - Python
🤖 From-scratch GPT in PyTorch — bigram, single-head & multi-head attention • FastAPI /generate endpoint • React + Vite frontend • Character-level tokenizer • CUDA support
react python machine-learning typescript deep-learning tokenizer text-generation pytorch embeddings transformer gpt language-model encoder-decoder character-level self-attention multi-head-attention fastapi nanogpt
-
Updated
Jul 8, 2026 - Python
In this project, I worked with a small corpus consisting of simple sentences. I tokenized the words using n-grams from the NLTK library and performed word-level and character-level one-hot encoding. Additionally, I utilized the Keras Tokenizer to tokenize the sentences and implemented word embedding using the Embedding layer. For sentiment analysis
word-embeddings corpus seq2seq ngrams character-level character-level-language-model word-level-language-model one-hot-encoding pre-trained-word-embedding pre-trained-glove-6b word-level
-
Updated
Aug 1, 2023 - Jupyter Notebook
Um GPT em nível de caractere escrito do zero em Java puro, sem bibliotecas de machine learning. Três níveis: bigrama por contagem, MLP com backpropagation manual e um Transformer com atenção causal.
java nlp machine-learning deep-learning neural-network maven transformer educational gpt portuguese language-model attention-mechanism backpropagation from-scratch autodiff character-level java21
-
Updated
Sep 7, 2026 - TypeScript
build your own GPT, one letter at a time - a character-level GPT trained from scratch on public-domain books: trainer, corpus pipeline, benchmark harness, and 5 trained models
nlp education benchmark deep-learning pytorch transformer public-domain gpt language-model character-level llm nanogpt
-
Updated
Jul 10, 2026 - Python
Character-level vanilla RNN in PyTorch that predicts a name's language of origin, letter by letter. Includes training, confusion matrix evaluation, and inference — plus a real example of dataset distribution shift when tested on modern names.
-
Updated
Sep 7, 2026 - Jupyter Notebook
TinyTalker is a small GPT model based on a character level tokenization system built from scratch. You can prompt it or train it on your own data super easily. It is also super small and can be ran on laptops.
machine-learning deep-learning text-generation pytorch transformer educational gpt language-model character-level llm nanogpt small-language-model
-
Updated
Jun 6, 2025 - Python
TapeLM: facts as fingerprints on character ink — not token-id memory, not chunk RAG. One frozen curve encoder for generation and structured slot memory (write, bind, hop, resolve). Noisy recall, lexicon calibration, one-shot edits, clean unlearning — vs fair GPT/RAG; reproducible JSON benchmarks.
nlp conflict-resolution information-retrieval reproducible-research fp pytorch bindings calibration representation-learning language-model cross-domain character-level machine-unlearning episodic-memory memory-augmented-neural-networks knowledge-editing retrieval-augmented-generation research-code frozen-backbone
-
Updated
Aug 25, 2026 - Python
A decoder-only GPT built from scratch in pure PyTorch — no nn.Transformer, no HuggingFace. Character-level, writes pseudo-Shakespeare in ~20 min on a laptop CPU. Streaming web playground, 31 tests, every design choice motivated inline.
education machine-learning ai deep-learning neural-network pytorch transformer educational attention gpt language-model from-scratch character-level self-attention mingpt llm nanogpt
-
Updated
Jul 7, 2026 - Python
Character-level GPT with six-part attention head analysis — ablation, head patching, residual patching, redundancy testing, seed robustness, and logit lens — converging on one load-bearing head.
pytorch transformer attention gpt interpretability character-level mechanistic-interpretability activation-patching
-
Updated
Jul 17, 2026 - Python
An implementation of character level text generation with LSTM.
-
Updated
Oct 29, 2020 - Jupyter Notebook
Optimized LSTM-based character-level text generator trained on Shakespeare, achieving 3.5x faster training with mixed precision.
python nlp machine-learning natural-language-processing deep-learning text-generation pytorch lstm neural-networks rnn academic-project shakespeare character-level gpu-optimization mixed-precision
-
Updated
Sep 25, 2025 - Python
Bit-exact MicroGPT inference in pure SQLite SQL—not text-to-SQL. Integer-only Q16.48 transformer math and deterministic sampling, with no UDFs or extensions.
sql sqlite transformers inference transformer fixed-point reproducibility quantization deterministic from-scratch character-level pure-sql llm integer-only bit-exact
-
Updated
Aug 26, 2026 - C
Character-level fork of Fairseq for sequence-to-sequence learning
transliteration seq2seq sequence-to-sequence char-level-cnn character-level fairseq char-level-rnn char-level-lstm
-
Updated
Oct 23, 2018 - Python
Character-level language model series from bigram to WaveNet, with probing analysis of learned phonological representations.
neural-network pytorch representation-learning language-model interpretability character-level probing
-
Updated
Jul 8, 2026 - Python
Add this topic to your repo
To associate your repository with the character-level topic, visit your repo's landing page and select "manage topics."