Search Results for "corpus"
Sort By:
26 projects for "corpus" with 2 filters applied:
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
1
ArXiv MCP Server
A Model Context Protocol server for searching and analyzing arXiv
...Issue threads show feature requests such as extracting embedded LaTeX and improving markdown conversion, reflecting active community use in research flows. It’s designed to be drop-in for MCP clients, giving them typed inputs/outputs and predictable errors around a well-known academic corpus. For developers building research copilots, it removes the glue work of wiring arXiv APIs into an agent toolchain. -
2
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
3
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
...This design helps decouple semantic and acoustic information while preserving fine-grained prosody, leading to more stable and expressive generation than many discrete-token systems. Trained on a large 1.8-million-hour bilingual corpus, VoxCPM can infer appropriate speaking style from context, dynamically adjusting intonation, rhythm, and emotional tone. It supports zero-shot voice cloning from a short reference audio clip, capturing timbre, accent, and pacing to closely mimic a target speaker without per-speaker fine-tuning. -
4
DeepSeek Coder
DeepSeek Coder: Let the Code Write Itself
DeepSeek-Coder is a series of code-specialized language models designed to generate, complete, and infill code (and mixed code + natural language) with high fluency in both English and Chinese. The models are trained from scratch on a massive corpus (~2 trillion tokens), of which about 87% is code and 13% is natural language. This dataset covers project-level code structure (not just line-by-line snippets), using a large context window (e.g. 16K) and a secondary fill-in-the-blank objective to encourage better contextual completions and infilling. Multiple sizes of the model are offered (e.g. 1B, 5.7B, 6.7B, 33B) so users can trade off inference cost vs capability. ... -
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
FlexLLMGen
Running large language models on a single GPU
...This design allows organizations to deploy powerful language models for high-volume tasks without the infrastructure costs typically associated with large-scale AI systems. The project is particularly useful for workloads that prioritize throughput over latency, including benchmarking experiments and large corpus analysis. -
6
Step3-VL-10B
Multimodal model achieving SOTA performance
...Despite having only about 10 billion parameters, it delivers performance that rivals or even surpasses much larger models (10×–20× larger) on a wide range of multimodal benchmarks covering reasoning, perception, and complex tasks, positioning it as one of the most powerful models in its class. It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
7
nanochat
The best ChatGPT that $100 can buy
nanochat is a from-scratch, end-to-end “mini ChatGPT” that shows the entire path from raw text to a chatty web app in one small, dependency-lean codebase. The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. ... -
8
OSS-Fuzz Gen
LLM powered fuzzing via OSS-Fuzz
...The system integrates with modern LLM-assisted workflows to draft harness code and then iterates based on build errors or low coverage signals. Importantly, it aligns with OSS-Fuzz conventions, generating corpus seeds, build rules, and sanitizer settings so projects can plug in quickly. Reports highlight what functions were targeted, how coverage evolved, and where manual hints could unlock more paths. The goal is pragmatic: shrink the gap between “we should fuzz this” and “we have robust fuzzing running in CI,” especially for understaffed maintainers. -
9
Paul Graham GPT
RAG on Paul Graham's essays
Paul Graham GPT is a specialized AI-powered search and chat app built on a corpus of essays from Paul Graham, giving users the ability to query and discuss his writings in a conversational way. The repo stores the full text of his essays (chunked), uses embeddings (e.g. via OpenAI embeddings) to allow semantic search over that corpus, and hosts a chat interface that combines retrieval results with LLM-based answering — enabling RAG (retrieval-augmented generation) over a fixed dataset. ... -
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.
-
10
Retrieval-Based Conversational Model
Dual LSTM Encoder for Dialog Response Generation
...The core idea is to embed both the conversation context and potential replies into vector representations, then score how well each candidate fits the current dialogue, choosing the best match accordingly. Designed to work with datasets like the Ubuntu Dialogue Corpus, this codebase includes data preparation, model training, and evaluation components for building and assessing dialog models that can handle multi-turn conversations. -
11
mwetoolkit
THIS PROJECT MIGRATED TO https://gitlab.com/mwetoolkit/mwetoolkit3/
...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 applied to virtually any text collection, language, and MWE type. It is a command-line tool written mostly in Python. Its development started in 2010 as a PhD thesis but the project keeps active (see the SVN logs). Up-to-date documentation and details about the tool can be found on the mwetoolkit website: http://mwetoolkit.sourceforge.net/ -
12
The Deep Email Miner Application is a software solution for the multistaged analysis of an Email Corpus. Social network analysis and text mining techniques are connected to enable an in depth view into the underlying information. The self-executable Version 1.1 jar file will now run on Java 1.5 or higher. A Windows executable file of Version 1.1 is also provided in the Files section. Documentation can be found on the project homepage.
-
13
CRFSharp
CRFSharp is a .NET(C#) implementation of Conditional Random Field
...It encodes model parameters by L-BFGS. Moreover, it has many significant improvement than CRF++, such as totally parallel encoding, optimizing memory usage and so on. Currently, when training corpus, compared with CRF++, CRF# can make full use of multi-core CPUs and only uses very low memory, and memory grow is very smoothly and slowly while amount of training corpus, tags increase. with multi-threads process, CRF# is more suitable for large data and tags training than CRF++ now. For example, in machine with 64GB, CRF# encodes model with more than 4.5 hundred million features quickly. -
14
This project aims to build a suite of Natural Language Processing tools. Modules will include corpus indexing and access tools, a part-of-speech tagger, tokenisers, text classification software, etc.
-
15
-
16
Cunei is a data-driven machine translation system that builds dynamic, statistical models based on instances of known translations found in a corpus.
-
17
Sanchay is a collection of tools and APIs for language researchers. It has some implementations of NLP algorithms, some flexible APIs, several user friendly annotation interfaces and Sanchay Query Language for language resources.
-
18
BabyTALK is to add another brick in the wall of natural languages learning. The baby needs to structure a corpus of texts when his tutor points and talks about a particular part of the corpus. The baby is also to describe any selected part of the corpus.
-
19
CRFChunker: Conditional Random Fields Phrase Chunker (Phrase Chunking Tool) for English. The model was trained on sections 01..24 of WSJ corpus and using section 00 as the development test set (F1-score of 95.77). Chunking speed: 700 sentences/s
-
20
CRFTagger: Conditional Random Fields Part-of-Speech (POS) Tagger for English. The model was trained on sections 01..24 of WSJ corpus and using section 00 as the development test set (accuracy of 97.00%). Tagging speed: 500 sentences/s.
-
21
A research corpus for knowledge representation and reasoning, with problems drawn from the domain of history.
-
22
CoPT, Corpus Processing Tools, is a set of java classes intended to assist field linguists, NLP researchers and developers, students and software developers in all corpus-related processing.
-
23
Hermes 4
Hermes 4 FP8: hybrid reasoning Llama-3.1-405B model by Nous Research
...It introduces a hybrid reasoning mode with explicit <think> segments, enabling the model to deliberate deeply when needed and switch to faster responses when desired. Post-training improvements include a vastly expanded corpus with ~60B tokens, boosting performance across math, code, STEM, logic, creativity, and structured outputs. The model is designed for schema adherence, producing valid JSON and repairing malformed outputs, making it highly suitable for tool use and function calling. Hermes 4 is engineered for superior steerability with reduced refusal rates, aligning responses to user values while preserving assistant quality. ... -
24
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. ... -
25
GigaChat 3 Ultra
High-performance MoE model with MLA, MTP, and multilingual reasoning
...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. This combination significantly boosts reasoning, coding, and multilingual performance across modern benchmarks. Designed for high-performance deployment, GigaChat 3 Ultra supports major inference engines and offers optimized BF16 and FP8 execution paths for cluster-grade hardware.
