40 packages found

node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
  1. llama
  2. llama-cpp
  3. llama.cpp
  4. bindings
  5. ai
  6. cmake
  7. cmake-js
  8. prebuilt-binaries
  9. llm
  10. gguf
  11. metal
  12. cuda
  13. vulkan
  14. grammar
  15. embedding
  16. rerank
  17. reranking
  18. json-grammar
  19. json-schema-grammar
  20. functions
  21. function-calling
  22. token-prediction
  23. speculative-decoding
  24. temperature
  25. minP
  26. topK
  27. topP
  28. seed
  29. json-schema
  30. raspberry-pi
  31. self-hosted
  32. local
  33. catai
  34. mistral
  35. deepseek
  36. qwen
  37. qwq
  38. typescript
  39. lora
  40. batching
  41. gpu
  42. nodejs
3.7.0published 3 weeks agoMIT

typia

Superfast runtime validators with only one line
  1. fast
  2. json
  3. stringify
  4. typescript
  5. transform
  6. ajv
  7. io-ts
  8. zod
  9. schema
  10. json-schema
  11. generator
  12. assert
  13. clone
  14. is
  15. validate
  16. equal
  17. runtime
  18. type
  19. typebox
  20. checker
  21. validator
  22. safe
  23. parse
  24. prune
  25. random
  26. protobuf
  27. llm
  28. llm-function-calling
  29. structured-output
  30. openai
  31. chatgpt
  32. claude
  33. gemini
  34. llama
  35. agentic-ai
  36. hacktoberfest
  37. openapi
84 Contributors
9.1.1published 1 week agoMIT

nano-bots

Ruby Implementation of Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as OpenAI ChatGPT, Ollama, Mistral AI, Cohere Command, Maritaca AI MariTalk, and Google Gemini, with support for calling Tools (Functions).
  1. anthropic
  2. anthropic-claude
  3. chatgpt
  4. cohere-ai
  5. gemini
  6. gemini-pro
  7. google-ai
  8. google-gemini
  9. google-vertex-ai
  10. gpt
  11. gpt-4
  12. llama
  13. llm
  14. maritaca-ai
  15. mistral
  16. mistral-ai
  17. nano-bots
  18. ollama
  19. openai
  20. openai-api
1 Contributors
3.4.0published 10 months agoMIT

py-data-juicer

A One-Stop Data Processing System for Large Language Models.
  1. chinese
  2. data-analysis
  3. data-science
  4. data-visualization
  5. dataset
  6. gpt
  7. gpt-4
  8. instruction-tuning
  9. large-language-models
  10. llama
  11. llava
  12. llm
  13. llms
  14. multi-modal
  15. nlp
  16. opendata
  17. pre-training
  18. pytorch
  19. streamlit
  20. synthetic-data
28 Contributors
1.3.1published 6 days agoApache-2.0

paddle-pipelines

Paddle-Pipelines: An End to End Natural Language Proceessing Development Kit Based on PaddleNLP
  1. bert
  2. compression
  3. distributed-training
  4. document-intelligence
  5. embedding
  6. ernie
  7. information-extraction
  8. llama
  9. llm
  10. neural-search
  11. nlp
  12. paddlenlp
  13. pretrained-models
  14. question-answering
  15. search-engine
  16. semantic-analysis
  17. sentiment-analysis
  18. transformers
  19. uie
334 Contributors
0.6.2published 1 year agoApache-2.0

ludwig

Declarative machine learning: End-to-end machine learning pipelines using data-driven configurations.
  1. ludwig
  2. deep
  3. learning
  4. deep_learning
  5. machine
  6. machine_learning
  7. natural
  8. language
  9. processing
  10. computer
  11. vision
  12. computer-vision
  13. data-centric
  14. data-science
  15. deep-learning
  16. deeplearning
  17. fine-tuning
  18. llama
  19. llama2
  20. llm
  21. llm-training
  22. machine-learning
  23. machinelearning
  24. mistral
  25. ml
  26. natural-language
  27. natural-language-processing
  28. neural-network
  29. pytorch
150 Contributors
0.10.4published 9 months agoApache-2.0

poe-api-wrapper

A simple, lightweight and efficient API wrapper for Poe.com
  1. python
  2. poe
  3. quora
  4. chatgpt
  5. claude
  6. poe-api
  7. api
  8. chatbot
  9. code-llama
  10. dall-e
  11. gemini
  12. gpt-4
  13. groq
  14. llama
  15. mistral
  16. openai
  17. palm2
  18. qwen
  19. reverse-engineering
  20. stable-diffusion
5 Contributors
1.7.0published 5 months agoGPL-3.0

sglang

SGLang is yet another fast serving framework for large language models and vision language models.
  1. cuda
  2. deepseek
  3. deepseek-llm
  4. deepseek-r1
  5. deepseek-r1-zero
  6. deepseek-v3
  7. inference
  8. llama
  9. llama3
  10. llama3-1
  11. llava
  12. llm
  13. llm-serving
  14. moe
  15. pytorch
  16. transformer
  17. vlm
335 Contributors
0.4.5.post1published 1 day agoOther

ms-swift

Swift: Scalable lightWeight Infrastructure for Fine-Tuning
  1. python
  2. petl
  3. efficient
  4. tuners
  5. deepseek-r1
  6. deploy
  7. distill
  8. embedding
  9. grpo
  10. internvl
  11. liger
  12. llama
  13. llama4
  14. llm
  15. lora
  16. megatron
  17. multimodal
  18. omni
  19. open-r1
  20. peft
  21. qwen2-5
  22. qwen2-vl
  23. rft
  24. sft
55 Contributors
3.3.0.post1published 5 days agoApache-2.0

unsloth-zoo

Utils for Unsloth
  1. ai
  2. llm
  3. deepseek
  4. deepseek-r1
  5. fine-tuning
  6. finetuning
  7. gemma
  8. gemma2
  9. gemma3
  10. llama
  11. llama3
  12. llms
  13. lora
  14. mistral
  15. phi3
  16. qlora
  17. unsloth
32 Contributors
2025.3.17published 3 weeks agoApache-2.0
Showing 1 to 10 of 40 results