CodeTF
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM
Stars: 1462
CodeTF is a Python transformer-based library for code large language models (Code LLMs) and code intelligence. It provides an interface for training and inferencing on tasks like code summarization, translation, and generation. The library offers utilities for code manipulation across various languages, including easy extraction of code attributes. Using tree-sitter as its core AST parser, CodeTF enables parsing of function names, comments, and variable names. It supports fast model serving, fine-tuning of LLMs, various code intelligence tasks, preprocessed datasets, model evaluation, pretrained and fine-tuned models, and utilities to manipulate source code. CodeTF aims to facilitate the integration of state-of-the-art Code LLMs into real-world applications, ensuring a user-friendly environment for code intelligence tasks.
README:
CodeTF is a one-stop Python transformer-based library for code large language models (Code LLMs) and code intelligence, provides a seamless interface for training and inferencing on code intelligence tasks like code summarization, translation, code generation and so on. It aims to facilitate easy integration of SOTA CodeLLMs into real-world applications.
In addition to the core LLMs's features for code, CodeTF offers utilities for code manipulation across various languages, including easy extraction of code attributes. Using tree-sitter as its core AST parser, it enables parsing of attributes such as function names, comments, and variable names. Pre-built libraries for numerous languages are provided, eliminating the need for complicated parser setup. CodeTF thus ensures a user-friendly and accessible environment for code intelligence tasks.
The current version of the library offers:
- Fast Model Serving: We support an easy-to-use interface for rapid inferencing with pre-quantized models (int8, int16, float16). CodeTF handles all aspects of device management, so users do not have to worry about that aspect. If your model is large, we offer advanced features such as weight sharding across GPUs to serve the models more quickly.
- Fine-Tuning Your Own Models: We provide an API for quickly fine-tuning your own LLMs for code using SOTA techniques for parameter-efficient fine-tuning (HuggingFace PEFT) on distributed environments.
- Supported Tasks: nl2code, code summarization, code completion, code translation, code refinement, clone detection, defect prediction.
- Datasets+: We have preprocessed well-known benchmarks (Human-Eval, MBPP, CodeXGLUE, APPS, etc.) and offer an easy-to-load feature for these datasets.
- Model Evaluator: We provide interface to evaluate models on well-known benchmarks (e.g. Human-Eval) on popular metrics (e.g., pass@k) with little effort (~15 LOCs).
- Pretrained Models: We supply pretrained checkpoints of state-of-the-art foundational language models of code (CodeBERT, CodeT5, CodeGen, CodeT5+, Incoder, StarCoder, etc.).
- Fine-Tuned Models: We furnish fine-tuned checkpoints for 8+ downstream tasks.
- Utility to Manipulate Source Code: We provide utilities to easily manipulate source code, such as user-friendly AST parsers (based on tree-sitter) in 15+ programming languages, to extract important code features, such as function name, identifiers, etc.
The following table shows the supported models with sizes and the tasks that the models support. This is a continuing effort and we are working on further growing the list.
| Model | Size | Tasks |
|---|---|---|
| CodeT5 | Base, Base-multi-sum, Base-translate-cs, Base-translate-java, Base-sum, Base-clone, Base-defect | Pretrained, NL to Code, Refine, Translation (CS to Java, Java to CS), Summarization (Python, Go, PHP, JavaScript, Java, Ruby), Clone detection, Defect prediction |
| CodeT5+ | Plus-instruct-16B, Plus-16B, Plus-6B, Plus-2B, Plus-770M-python, Plus-770M, Plus-220M | Pretrained, NL to Code, Refine , Defect prediction |
| CodeGen | Mono: 350M, 2B, 6B, 1B, 3.7B, 7B, 16B Multi: 350M, 2B, 6B NL: 350M, 2B |
Pretrained |
| StarCoder | 15.5B | Pretrained |
| SantaCoder | 1.1B | Pretrained |
| GPT-NeoX | 20B | Pretrained |
| GPT-Neo | 1.3B | Pretrained |
| GPT-J | 6B | Pretrained |
| Incoder | 6B | Pretrained |
| CodeParrot | Small-python (110M), Small-multi(110M), 1.5B | Pretrained |
| CodeBERT | CodeBERT-base, UnixCoder-base, CodeBERTa-small | Pretrained |
- (Optional) Creating conda environment
conda create -n codetf python=3.8
conda activate codetf- Install from PyPI:
pip install salesforce-codetf- Alternatively, build CodeTF from source:
git clone https://github.com/salesforce/CodeTF.git
cd CodeTF
pip install -e .Additionally, to make sure the quantization feature works well, also install these dependencies:
pip install -q -U git+https://github.com/huggingface/transformers.git
pip install -q -U git+https://github.com/huggingface/peft.git
pip install -q -U git+https://github.com/huggingface/accelerate.gitFor some models, such as StarCoder, it is required to log in Huggingface. Please obtain the HuggingFace token and login:
huggingface-cli login
Getting started with CodeTF is simple and quick with our model loading pipeline function load_model_pipeline(). Here's an example showing how to load codet5+ model and perform inference on code generation task:
from codetf.models import load_model_pipeline
code_generation_model = load_model_pipeline(model_name="codet5", task="pretrained",
model_type="plus-770M-python", is_eval=True,
load_in_8bit=True, load_in_4bit=False, weight_sharding=False)
result = code_generation_model.predict(["def print_hello_world():"])
print(result)There are a few notable arguments that need to be considered:
-
model_name: the name of the model, currently supportcodet5andcausal-lm. -
model_type: type of model for each model name, e.g.base,codegen-350M-mono,j-6B, etc. -
load_in_8bitandload_in_4bit: inherit the dynamic quantization feature from Huggingface Quantization. -
weight_sharding: our advance feature that leverages HuggingFace Sharded Checkpoint to split a large model in several smaller shards in different GPUs. Please consider using this if you are dealing with large models.
You might want to view all of the supported models. To do this, you can use the model_zoo():
from codetf.models import model_zoo
print(model_zoo)
# ============================================================================================================
# Architectures Types Tasks
# ============================================================================================================
# causallm codegen-350M-mono pretrained
# codegen-350M-multi pretrained
# codegen-350M-nl pretrained
# codegen-2B-mono pretrained
# codegen-2B-multi pretrained
# codegen-2B-nl pretrained
# codegen-6B-mono pretrained
# codegen-6B-nl pretrained
# codegen-6B-multi pretrained
# starcoder-15.5B pretrained
# gpt-neox-20B pretrained
# gpt-neo-1.3B pretrained
# gpt-j-6B pretrained
# incoder-6B pretrained
# codegen2-1B pretrained
# codegen2-3.7B pretrained
# codegen2-7B pretrained
# codegen2-16B pretrained
# codet5 base-multi-sum pretrained
# base nl2code
# base refine
# base translate_cs_java
# base translate_java_cs
# base sum_python
# base sum_go
# base sum_php
# base sum_javascript
# base sum_java
# base sum_ruby
# base clone
# base defect
# plus-instruct-16B pretrained
# plus-16B pretrained
# plus-6B pretrained
# plus-2B pretrained
# plus-770M-python pretrained
# plus-770M pretrained
# plus-220M pretrained
# bert codebert-base pretrained
# unixcoder-base pretrained
# codeberta-small pretrainedWant to train a custom LLM for code? We've got you covered. Below is an example using the Seq2SeqTrainer to fine-tune a CodeT5+ pretrained model, along with our dataset utilities, make it easy to fine-tune your models using the CodeXGLUE dataset. Here's an example:
from codetf.trainer.codet5_trainer import CodeT5Seq2SeqTrainer
from codetf.data_utility.codexglue_dataset import CodeXGLUEDataset
from codetf.models import load_model_pipeline
from codetf.performance.evaluation_metric import EvaluationMetric
from codetf.data_utility.base_dataset import CustomDataset
model_class = load_model_pipeline(model_name="codet5", task="pretrained",
model_type="plus-220M", is_eval=True)
dataset = CodeXGLUEDataset(tokenizer=model_class.get_tokenizer())
train, test, validation = dataset.load(subset="text-to-code")
train_dataset= CustomDataset(train[0], train[1])
test_dataset= CustomDataset(test[0], test[1])
val_dataset= CustomDataset(validation[0], validation[1])
evaluator = EvaluationMetric(metric="bleu", tokenizer=model_class.tokenizer)
# peft can be in ["lora", "prefixtuning"]
trainer = CodeT5Seq2SeqTrainer(train_dataset=train_dataset,
validation_dataset=val_dataset,
peft="lora",
pretrained_model_or_path=model_class.get_model(),
tokenizer=model_class.tokenizer)
trainer.train()Comparing to this script from StarCoder, which requires ~300 LOCs to fine-tune a model, we only need 14 LOCs to do the same !!!
Planning to reproduce the results of well-known benchmarks like Human-Eval, but struggling with not achieving the same numbers as reported in the original papers? Worried about the complicated evaluation process? Don't worry, we've got you covered with an intuitive, easy-to-use interface. Here's a sample snippet demonstrating how to evaluate Human Eval using pass@k (k=[1,10,100]) as the metric:
from codetf.models import load_model_pipeline
from codetf.data_utility.human_eval_dataset import HumanEvalDataset
from codetf.performance.model_evaluator import ModelEvaluator
os.environ["HF_ALLOW_CODE_EVAL"] = "1"
os.environ["TOKENIZERS_PARALLELISM"] = "true"
model_class = load_model_pipeline(model_name="causal-lm", task="pretrained",
model_type="codegen-350M-mono", is_eval=True,
load_in_8bit=True, weight_sharding=False)
dataset = HumanEvalDataset(tokenizer=model_class.get_tokenizer())
prompt_token_ids, prompt_attention_masks, references= dataset.load()
problems = TensorDataset(prompt_token_ids, prompt_attention_masks)
evaluator = ModelEvaluator(model_class)
avg_pass_at_k = evaluator.evaluate_pass_k(problems=problems, unit_tests=references)
print("Pass@k: ", avg_pass_at_k)Comparing to this script from HuggingFace, which requires ~230 LOCs to evaluate on pass@k, we only need 14 LOCs to do the same !!!
CodeTF provides the Dataset utility for several well-known datasets, such as CodeXGLUE, Human Eval, MBPP, and APPS. The following is an example of how to load the CodeXGLUE dataset:
from codetf.data_utility.codexglue_dataset import CodeXGLUEDataset
from transformers import RobertaTokenizer
tokenizer = RobertaTokenizer.from_pretrained("Salesforce/codet5-base", use_fast=True)
dataset = CodeXGLUEDataset(tokenizer=tokenizer)
train, test, validation = dataset.load(subset="text-to-code")The train, test, validation are returned in form of Pytorch tensor to provide the flexilbity for the users to wrap it into higher-lever wrapper for their own use cases.
In addition to providing utilities for LLMs, CodeTF also equips users with tools for effective source code manipulation. This is crucial in the code intelligence pipeline, where operations like parsing code into an Abstract Syntax Tree (AST) or extracting code attributes (such as function names or identifiers) are often required (CodeT5). These tasks can be challenging to execute, especially when setup and multi-language support is needed. Our code utility interface offers a streamlined solution, facilitating easy parsing and attribute extraction from code across 15+ languages.
CodeTF includes AST parsers compatible with numerous programming languages. Here's an example showcasing the parsing of Apex code into an AST:
from codetf.code_utility.apex.apex_code_utility import ApexCodeUtility
apex_code_utility = ApexCodeUtility()
sample_code = """
public class SampleClass {
public Integer myNumber;
**
* This is a method that returns the value of myNumber.
* @return An integer value
*/
public Integer getMyNumber() {
// Return the current value of myNumber
return this.myNumber;
}
}
"""
ast = apex_code_utility.parse(sample_code)
# This will print the tree-sitter AST object
print(ast)Then you can traverse the tree using the interface from py-tree-sitter
root_node = ast.root_node
assert root_node.type == 'module'
assert root_node.start_point == (1, 0)
assert root_node.end_point == (3, 13)
There are also other utilities for Java, Python, etc, that can perform the same operations.
CodeTF provides an interface to easily extract code attributes. The following is a sample for extracting the function name of a Python function:
code_attributes = apex_code_utility.get_code_attributes(sample_code)
print(code_attributes)This will print:
{'class_names': ['AccountWithContacts'], 'method_names': ['getAccountsWithContacts'], 'comments': [], 'variable_names': ['acc', 'accounts', 'con', 'System', 'debug', 'Contacts', 'Id', 'Name', 'Account', 'Email', 'LastName']}
There are other existing utilities, such as removing comments from code:
new_code_snippet = apex_code_utility.remove_comments(sample_code)
print(new_code_snippet)This will print:
public class SampleClass {
public Integer myNumber;
public Integer getMyNumber() {
return this.myNumber;
}
}Note that this is an ongoing process, we will add more features to extract complicated code attributes in the future. More examples can be found here.
You can find more examples for each use case:
- CodeTF is designed to complement and enhance the capabilities of HuggingFace Transformers, rather than replace it. It serves as a specialized layer specifically tailored for code intelligence tasks, such as fine-tuning language models with code-specific features and evaluating on well-known code intelligence benchmarks. If users require more customization, they are encouraged to write their own training code from scratch.
- CodeTF leverages the powerful functionality provided by Accelerate for both inference and training. With Accelerate, users do not need to manually manage GPUs or CPU devices for most operations, allowing for a streamlined and efficient workflow.
CodeTF, while powerful, does not guarantee infallible code intelligence capabilities. Users may encounter inaccuracies or biases, possibly leading to misinterpretations or undesired behaviors. Risks include the generation of insecure code, propagation of poor coding practices, or inadvertent revelation of sensitive data. We strongly advise users to examine the pretrained models and system before practical adoption. CodeTF facilitates effective code analysis, prediction, and debugging, promoting reproducible research and development. We encourage its responsible use for enhancing software quality and developer productivity.
However, misuse can lead to unethical outcomes such as unauthorized code manipulation, privacy breaches, or insecure coding practices. Users should familiarize themselves with guidelines for responsible AI before using CodeTF. Our commitment is to continually refine the library by identifying and mitigating potential biases and inappropriate behaviors. Users should review the models and system before practical implementation, and contribute towards refining the library to ensure ethical usage.
You can find more details in our technical report.
If you're using CodeTF in your research or applications, please cite using this BibTeX:
@misc{nghi2023codetf,
title={CodeTF: A Transformer-based Library for CodeLLM & Code Intelligence},
author={Nghi D. Q. Bui, Henry Le, Yue Wang, Akhilesh Deepak Gotmare, Junnan Li, Steven Hoi.},
year={2023},
eprint={2209.09019},
archivePrefix={arXiv},
primaryClass={cs.CV}
}If you have any questions, comments or suggestions, please do not hesitate to contact us at [email protected].
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for CodeTF
Similar Open Source Tools
CodeTF
CodeTF is a Python transformer-based library for code large language models (Code LLMs) and code intelligence. It provides an interface for training and inferencing on tasks like code summarization, translation, and generation. The library offers utilities for code manipulation across various languages, including easy extraction of code attributes. Using tree-sitter as its core AST parser, CodeTF enables parsing of function names, comments, and variable names. It supports fast model serving, fine-tuning of LLMs, various code intelligence tasks, preprocessed datasets, model evaluation, pretrained and fine-tuned models, and utilities to manipulate source code. CodeTF aims to facilitate the integration of state-of-the-art Code LLMs into real-world applications, ensuring a user-friendly environment for code intelligence tasks.
litdata
LitData is a tool designed for blazingly fast, distributed streaming of training data from any cloud storage. It allows users to transform and optimize data in cloud storage environments efficiently and intuitively, supporting various data types like images, text, video, audio, geo-spatial, and multimodal data. LitData integrates smoothly with frameworks such as LitGPT and PyTorch, enabling seamless streaming of data to multiple machines. Key features include multi-GPU/multi-node support, easy data mixing, pause & resume functionality, support for profiling, memory footprint reduction, cache size configuration, and on-prem optimizations. The tool also provides benchmarks for measuring streaming speed and conversion efficiency, along with runnable templates for different data types. LitData enables infinite cloud data processing by utilizing the Lightning.ai platform to scale data processing with optimized machines.
openvino.genai
The GenAI repository contains pipelines that implement image and text generation tasks. The implementation uses OpenVINO capabilities to optimize the pipelines. Each sample covers a family of models and suggests certain modifications to adapt the code to specific needs. It includes the following pipelines: 1. Benchmarking script for large language models 2. Text generation C++ samples that support most popular models like LLaMA 2 3. Stable Diffuison (with LoRA) C++ image generation pipeline 4. Latent Consistency Model (with LoRA) C++ image generation pipeline
beyondllm
Beyond LLM offers an all-in-one toolkit for experimentation, evaluation, and deployment of Retrieval-Augmented Generation (RAG) systems. It simplifies the process with automated integration, customizable evaluation metrics, and support for various Large Language Models (LLMs) tailored to specific needs. The aim is to reduce LLM hallucination risks and enhance reliability.
rl
TorchRL is an open-source Reinforcement Learning (RL) library for PyTorch. It provides pytorch and **python-first** , low and high level abstractions for RL that are intended to be **efficient** , **modular** , **documented** and properly **tested**. The code is aimed at supporting research in RL. Most of it is written in python in a highly modular way, such that researchers can easily swap components, transform them or write new ones with little effort.
lionagi
LionAGI is a powerful intelligent workflow automation framework that introduces advanced ML models into any existing workflows and data infrastructure. It can interact with almost any model, run interactions in parallel for most models, produce structured pydantic outputs with flexible usage, automate workflow via graph based agents, use advanced prompting techniques, and more. LionAGI aims to provide a centralized agent-managed framework for "ML-powered tools coordination" and to dramatically lower the barrier of entries for creating use-case/domain specific tools. It is designed to be asynchronous only and requires Python 3.10 or higher.
composio
Composio is a production-ready toolset for AI agents that enables users to integrate AI agents with various agentic tools effortlessly. It provides support for over 100 tools across different categories, including popular softwares like GitHub, Notion, Linear, Gmail, Slack, and more. Composio ensures managed authorization with support for six different authentication protocols, offering better agentic accuracy and ease of use. Users can easily extend Composio with additional tools, frameworks, and authorization protocols. The toolset is designed to be embeddable and pluggable, allowing for seamless integration and consistent user experience.
zeta
Zeta is a tool designed to build state-of-the-art AI models faster by providing modular, high-performance, and scalable building blocks. It addresses the common issues faced while working with neural nets, such as chaotic codebases, lack of modularity, and low performance modules. Zeta emphasizes usability, modularity, and performance, and is currently used in hundreds of models across various GitHub repositories. It enables users to prototype, train, optimize, and deploy the latest SOTA neural nets into production. The tool offers various modules like FlashAttention, SwiGLUStacked, RelativePositionBias, FeedForward, BitLinear, PalmE, Unet, VisionEmbeddings, niva, FusedDenseGELUDense, FusedDropoutLayerNorm, MambaBlock, Film, hyper_optimize, DPO, and ZetaCloud for different tasks in AI model development.
ChatRex
ChatRex is a Multimodal Large Language Model (MLLM) designed to seamlessly integrate fine-grained object perception and robust language understanding. By adopting a decoupled architecture with a retrieval-based approach for object detection and leveraging high-resolution visual inputs, ChatRex addresses key challenges in perception tasks. It is powered by the Rexverse-2M dataset with diverse image-region-text annotations. ChatRex can be applied to various scenarios requiring fine-grained perception, such as object detection, grounded conversation, grounded image captioning, and region understanding.
hugging-chat-api
Unofficial HuggingChat Python API for creating chatbots, supporting features like image generation, web search, memorizing context, and changing LLMs. Users can log in, chat with the ChatBot, perform web searches, create new conversations, manage conversations, switch models, get conversation info, use assistants, and delete conversations. The API also includes a CLI mode with various commands for interacting with the tool. Users are advised not to use the application for high-stakes decisions or advice and to avoid high-frequency requests to preserve server resources.
pebblo
Pebblo enables developers to safely load data and promote their Gen AI app to deployment without worrying about the organization’s compliance and security requirements. The project identifies semantic topics and entities found in the loaded data and summarizes them on the UI or a PDF report.
wandb
Weights & Biases (W&B) is a platform that helps users build better machine learning models faster by tracking and visualizing all components of the machine learning pipeline, from datasets to production models. It offers tools for tracking, debugging, evaluating, and monitoring machine learning applications. W&B provides integrations with popular frameworks like PyTorch, TensorFlow/Keras, Hugging Face Transformers, PyTorch Lightning, XGBoost, and Sci-Kit Learn. Users can easily log metrics, visualize performance, and compare experiments using W&B. The platform also supports hosting options in the cloud or on private infrastructure, making it versatile for various deployment needs.
ivy
Ivy is an open-source machine learning framework that enables you to: * 🔄 **Convert code into any framework** : Use and build on top of any model, library, or device by converting any code from one framework to another using `ivy.transpile`. * ⚒️ **Write framework-agnostic code** : Write your code once in `ivy` and then choose the most appropriate ML framework as the backend to leverage all the benefits and tools. Join our growing community 🌍 to connect with people using Ivy. **Let's** unify.ai **together 🦾**
MotionLLM
MotionLLM is a framework for human behavior understanding that leverages Large Language Models (LLMs) to jointly model videos and motion sequences. It provides a unified training strategy, dataset MoVid, and MoVid-Bench for evaluating human behavior comprehension. The framework excels in captioning, spatial-temporal comprehension, and reasoning abilities.
PhoGPT
PhoGPT is an open-source 4B-parameter generative model series for Vietnamese, including the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. PhoGPT-4B is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length and a vocabulary of 20K token types. PhoGPT-4B-Chat is fine-tuned on instructional prompts and conversations, demonstrating superior performance. Users can run the model with inference engines like vLLM and Text Generation Inference, and fine-tune it using llm-foundry. However, PhoGPT has limitations in reasoning, coding, and mathematics tasks, and may generate harmful or biased responses.
LightRAG
LightRAG is a PyTorch library designed for building and optimizing Retriever-Agent-Generator (RAG) pipelines. It follows principles of simplicity, quality, and optimization, offering developers maximum customizability with minimal abstraction. The library includes components for model interaction, output parsing, and structured data generation. LightRAG facilitates tasks like providing explanations and examples for concepts through a question-answering pipeline.
For similar tasks
awesome-code-ai
A curated list of AI coding tools, including code completion, refactoring, and assistants. This list includes both open-source and commercial tools, as well as tools that are still in development. Some of the most popular AI coding tools include GitHub Copilot, CodiumAI, Codeium, Tabnine, and Replit Ghostwriter.
companion-vscode
Quack Companion is a VSCode extension that provides smart linting, code chat, and coding guideline curation for developers. It aims to enhance the coding experience by offering a new tab with features like curating software insights with the team, code chat similar to ChatGPT, smart linting, and upcoming code completion. The extension focuses on creating a smooth contribution experience for developers by turning contribution guidelines into a live pair coding experience, helping developers find starter contribution opportunities, and ensuring alignment between contribution goals and project priorities. Quack collects limited telemetry data to improve its services and products for developers, with options for anonymization and disabling telemetry available to users.
CodeGeeX4
CodeGeeX4-ALL-9B is an open-source multilingual code generation model based on GLM-4-9B, offering enhanced code generation capabilities. It supports functions like code completion, code interpreter, web search, function call, and repository-level code Q&A. The model has competitive performance on benchmarks like BigCodeBench and NaturalCodeBench, outperforming larger models in terms of speed and performance.
probsem
ProbSem is a repository that provides a framework to leverage large language models (LLMs) for assigning context-conditional probability distributions over queried strings. It supports OpenAI engines and HuggingFace CausalLM models, and is flexible for research applications in linguistics, cognitive science, program synthesis, and NLP. Users can define prompts, contexts, and queries to derive probability distributions over possible completions, enabling tasks like cloze completion, multiple-choice QA, semantic parsing, and code completion. The repository offers CLI and API interfaces for evaluation, with options to customize models, normalize scores, and adjust temperature for probability distributions.
are-copilots-local-yet
Current trends and state of the art for using open & local LLM models as copilots to complete code, generate projects, act as shell assistants, automatically fix bugs, and more. This document is a curated list of local Copilots, shell assistants, and related projects, intended to be a resource for those interested in a survey of the existing tools and to help developers discover the state of the art for projects like these.
chatgpt
The ChatGPT R package provides a set of features to assist in R coding. It includes addins like Ask ChatGPT, Comment selected code, Complete selected code, Create unit tests, Create variable name, Document code, Explain selected code, Find issues in the selected code, Optimize selected code, and Refactor selected code. Users can interact with ChatGPT to get code suggestions, explanations, and optimizations. The package helps in improving coding efficiency and quality by providing AI-powered assistance within the RStudio environment.
minuet-ai.nvim
Minuet AI is a Neovim plugin that integrates with nvim-cmp to provide AI-powered code completion using multiple AI providers such as OpenAI, Claude, Gemini, Codestral, and Huggingface. It offers customizable configuration options and streaming support for completion delivery. Users can manually invoke completion or use cost-effective models for auto-completion. The plugin requires API keys for supported AI providers and allows customization of system prompts. Minuet AI also supports changing providers, toggling auto-completion, and provides solutions for input delay issues. Integration with lazyvim is possible, and future plans include implementing RAG on the codebase and virtual text UI support.
vim-ollama
The 'vim-ollama' plugin for Vim adds Copilot-like code completion support using Ollama as a backend, enabling intelligent AI-based code completion and integrated chat support for code reviews. It does not rely on cloud services, preserving user privacy. The plugin communicates with Ollama via Python scripts for code completion and interactive chat, supporting Vim only. Users can configure LLM models for code completion tasks and interactive conversations, with detailed installation and usage instructions provided in the README.
For similar jobs
weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.
LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.
VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.
kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.
PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.
tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.
spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.
Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.