Search Results for "token" - Page 8
Sort By:
Showing 216 open source projects for "token"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Repo of Tree of Thoughts (ToT)
Implementation of "Tree of Thoughts
Language models are increasingly being deployed for general problem-solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem-solving. ... -
2
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
DiT (Diffusion Transformer) is a powerful architecture that applies transformer-based modeling directly to diffusion generative processes for high-quality image synthesis. Unlike CNN-based diffusion models, DiT represents the diffusion process in the latent space and processes image tokens through transformer blocks with learned positional encodings, offering scalability and superior sample quality. The model architecture parallels large language models but for image tokens—each block... -
3
revChatGPT
This app allows you to chat with ChatGPT using reverse-engineered API
...To get started with the app, you'll need to create an account on OpenAI's ChatGPT and save your credentials. You can choose from three authentication methods: Email/Password, Session token, or Access token. Once you have your credentials, you can select your authentication method in the sidebar and provide the required information. If you choose Email/Password, you'll need to provide your email and password. If you choose Session token, you'll need to provide your session token. If you choose Access token, you'll need to provide your access token. revChatGPT is a reverse-engineered ChatGPT API that is not affiliated with OpenAI. ... -
4
DreamBooth Dataset
Text-to-Image Diffusion Models for Subject-Driven Generation
DreamBooth is a research project and dataset repository representing the official assets for the DreamBooth technique, a method for fine-tuning text-to-image generative diffusion models so they can generate specific, personalized subjects from just a handful of example images. Originally developed by researchers at Google Research and Boston University, DreamBooth works by associating a unique identifier token with a small set of photos of a person, object, or style, enabling the model to produce diverse and accurate images of that subject in new contexts once fine-tuned. This method addresses a common limitation of general-purpose diffusion models, which often struggle to faithfully reproduce lesser-known or custom subjects without extensive retraining. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT
minGPT is a minimalist, educational re-implementation of the GPT (Generative Pretrained Transformer) architecture built in PyTorch, designed by Andrej Karpathy to expose the core structure of a transformer-based language model in as few lines of code as possible. It strips away extraneous bells and whistles, aiming to show how a sequence of token indices is fed into a stack of transformer blocks and then decoded into the next token probabilities, with both training and inference supported. Because the whole model is around 300 lines of code, users can follow each step—from embedding lookup, positional encodings, multi-head attention, feed-forward layers, to output heads—and thus demystify how GPT-style models work beneath the surface. ... -
6
CPT
CPT: A Pre-Trained Unbalanced Transformer
...Position Embeddings We extend the max_position_embeddings from 512 to 1024. We initialize the new version of models with the old version of checkpoints with vocabulary alignment. Token embeddings found in the old checkpoints are copied. And other newly added parameters are randomly initialized. We further train the new CPT & Chinese BART 50K steps with batch size 2048, max-seq-length 1024, peak learning rate 2e-5, and warmup ratio 0.1. Aiming to unify both NLU and NLG tasks, We propose a novel Chinese Pre-trained Un-balanced Transformer (CPT). -
7
Diffusers-Interpret
Model explainability for Diffusers
...Get explanations for your generated images. Install directly from PyPI. It is possible to visualize pixel attributions of the input image as a saliency map. diffusers-interpret also computes these token/pixel attributions for generating a particular part of the image. To analyze how a token in the input prompt influenced the generation, you can study the token attribution scores. You can also check all the images that the diffusion process generated at the end of each step. Gradient checkpointing also reduces GPU usage, but makes computations a bit slower. -
8
Discord Mass DM GO
The most popular Discord selfbot written in GO
...DMDGO is a Multi-threaded Discord Self-Bot primarily used for mass messaging users on Discord. It has numerous other quality features to enhance the user experience and allow the user to target the most users. Multiple Captcha APIs supported. Supports token & email:pass:token formats. Compatible with all major OS and Architectures. Proxyless. Supports HTTP(s), SOCKS5 and SOCKS4 proxies. Free & Open source. Emulates Discord's requests to a very high accuracy to prevent detection. Highly Documented. Multi-threaded using Light-weight Goroutines supporting thousands of concurrent accounts. ... -
9
min(DALL·E)
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
...Use a positive seed for reproducible results. Higher values for supercondition_factor result in better agreement with the text but a narrower variety of generated images. Every image token is sampled from the top_k most probable tokens. The largest logit is subtracted from the logits to avoid infs. The logits are then divided by the temperature. If is_seamless is true, the image grid will be tiled in token space not pixel space. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
10
Hugging Face Transformer
CPU/GPU inference server for Hugging Face transformer models
Optimize and deploy in production Hugging Face Transformer models in a single command line. At Lefebvre Dalloz we run in-production semantic search engines in the legal domain, in the non-marketing language it's a re-ranker, and we based ours on Transformer. In that setup, latency is key to providing a good user experience, and relevancy inference is done online for hundreds of snippets per user query. Most tutorials on Transformer deployment in production are built over Pytorch and FastAPI.... -
11
Ecco
Explain, analyze, and visualize NLP language models
Ecco is an interpretability tool for transformers that helps visualize and analyze how language models generate text, making model behavior more transparent. -
12
Neuro-comma
Punctuation restoration production-ready model for Russian language
This library was developed with the idea to help us to create punctuation restoration models to memorize trained parameters, data, training visualization, etc. The Library doesn't use any high-level frameworks, such as PyTorch-lightning or Keras, to reduce the level entry threshold. Feel free to fork this repo and edit model or dataset classes for your purposes. Our team always uses the latest version and features of Python. We started with Python 3.9, but realized, that there is no FastAPI... -
13
Seq2seq Chatbot for Keras
This repository contains a new generative model of chatbot
This repository contains a new generative model of chatbot based on seq2seq modeling. The trained model available here used a small dataset composed of ~8K pairs of context (the last two utterances of the dialogue up to the current point) and respective response. The data were collected from dialogues of English courses online. This trained model can be fine-tuned using a closed-domain dataset to real-world applications. The canonical seq2seq model became popular in neural machine... -
14
mwetoolkit
THIS PROJECT MIGRATED TO https://gitlab.com/mwetoolkit/mwetoolkit3/
THIS PROJECT MIGRATED TO https://gitlab.com/mwetoolkit/mwetoolkit3/ The Multiword Expressions toolkit aids in the automatic identification and extraction of multiword units in running text. These include idioms (kick the bucket), noun compounds (cable car), phrasal verbs (take off, give up), etc. Even though it focuses on multiword expresisons, the framework is quite complete and can also be useful in any corpus-based study in computational linguistics. The mwetoolkit can be... -
15
Medical Treebank
Community-based linguistic annotation work on clinical documents.
This project hosts linguistic annotations and guidelines for clinical text. We plan to include several types of annotation (Token, POS and Parse) in WordFreak format on clinical notes originally from the i2b2/VA NLP challenges. The guidelines are copyrighted, but free for the community to use. Annotation in WordFreak format contains only linguistic labels and character offsets, and can be distributed independently from the note text. Instruction is provided on setting up WordFreak for aligning/visualizing the annotations with the source text, which should be obtained through the official i2b2 data host https://www.i2b2.org/NLP/DataSets/Main.php. -
16
Supernova programming language
Natural programming language for GUI applications
Modern scripting language and the first one that presents the concept of programming with direct fiction description using a clear subset of pure human language. Using Supernova you can write the source code using Arabic and/or English keywords and you can create GUI applications for Windows and Linux. -
17
These will be java based open source voice control player . These player can be controled by the uer voice .It can help thoushand of blind and physicaaly challanged person to enjoy the benifits of the music . And help in its development .
-
18
Nemotron 3
Large language model developed and released by NVIDIA
...The base Nano architecture uses a hybrid Mamba-Transformer Mixture-of-Experts (MoE) design, allowing the model to activate only a small fraction of its 31.6 billion parameters per token, which improves speed and efficiency without sacrificing quality on complex queries. This configuration supports a massive context length of up to 1 million tokens, making it suitable for long-context reasoning, agentic tasks, extended dialogues, and applications like code generation or document summarization. -
19
DiffusionGemma
NVFP4 DiffusionGemma model for fast multimodal text generation
...Built on the Gemma 4 26B A4B Mixture-of-Experts architecture, it has 25.2B total parameters and 3.8B active parameters, balancing capability with efficient inference. Its diffusion-based generation produces tokens in parallel 256-token blocks, enabling very high-speed output, with reported generation above 1,100 tokens per second on NVIDIA Hopper H100 in FP8. The model supports a 256K-token context window, configurable thinking mode, native function calling, structured JSON output, and multilingual inference across 35+ languages. The NVFP4 quantization reduces weights and activations from 16-bit to 4-bit, lowering disk size and GPU memory needs for vLLM deployment. -
20
MiMo-V2.5-Pro
Flagship MoE model for long-context agents and complex coding
...It features approximately 1.02 trillion total parameters with 42B activated per inference, balancing extreme capability with efficient execution. The model supports a 1 million token context window, enabling it to maintain coherence across long workflows involving thousands of tool calls and multi-step reasoning chains. Architecturally, it uses a hybrid attention system combining Sliding Window Attention and Global Attention to significantly reduce memory usage while preserving long-context performance. It also integrates multi-token prediction modules that accelerate inference and improve reinforcement learning efficiency. ... -
21
DeepSeek-V4-Flash
Efficient MoE model for million-token reasoning and coding
DeepSeek-V4-Flash is a preview Mixture-of-Experts language model built for efficient million-token context intelligence. It has 284B total parameters with 13B activated and supports a 1M-token context window, making it suitable for long-document reasoning, complex coding, agentic workflows, and large-scale information processing. The model uses a hybrid attention architecture that combines Compressed Sparse Attention and Heavily Compressed Attention to improve long-context efficiency, while Manifold-Constrained Hyper-Connections strengthen signal stability across layers. ... -
22
Laguna XS.2
Open agentic coding model optimized for local deployment
...The model features a 262K-token context window, preserved reasoning across interactions, FP8 KV-cache optimization, and compatibility with local deployment ecosystems such as Ollama and vLLM. -
23
MiMo-V2.5
Omnimodal AI model for agents, coding, and long-context tasks
...MiMo-V2.5 delivers near-Pro-level performance in coding, reasoning, and agent tasks while maintaining lower cost and faster inference speeds. It also integrates advanced components such as multi-token prediction modules and specialized vision and audio encoders, making it well-suited for autonomous agents and software development. -
24
GigaChat 3 Ultra
High-performance MoE model with MLA, MTP, and multilingual reasoning
...It leverages Multi-head Latent Attention to compress the KV cache into latent vectors, dramatically reducing memory demand and improving inference speed at scale. The model also employs Multi-Token Prediction, enabling multi-step token generation in a single pass for up to 40% faster output through speculative and parallel decoding techniques. Its training corpus incorporates ten languages, enriched with books, academic sources, code datasets, mathematical tasks, and more than 5.5 trillion tokens of high-quality synthetic data. ... -
25
roberta-base
Robust BERT-based model for English with improved MLM training
roberta-base is a robustly optimized variant of BERT, pretrained on a significantly larger corpus of English text using dynamic masked language modeling. Developed by Facebook AI, RoBERTa improves on BERT by removing the Next Sentence Prediction objective, using longer training, larger batches, and more data, including BookCorpus, English Wikipedia, CC-News, OpenWebText, and Stories. It captures contextual representations of language by masking 15% of input tokens and predicting them....
