unslothai/unsloth
5X faster 50% less memory LLM finetuning
Language: Python
#ai #finetuning #llm
Stars: 729 Issues: 8 Forks: 19
https://github.com/unslothai/unsloth
5X faster 50% less memory LLM finetuning
Language: Python
#ai #finetuning #llm
Stars: 729 Issues: 8 Forks: 19
https://github.com/unslothai/unsloth
GitHub
GitHub - unslothai/unsloth: Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory - unslothai/unsloth
SqueezeAILab/LLMCompiler
LLMCompiler: An LLM Compiler for Parallel Function Calling
Language: Python
#efficient_inference #function_calling #large_language_models #llama #llama2 #llm #llm_agent #llm_agents #llm_framework #llms #natural_language_processing #nlp #parallel_function_call #transformer
Stars: 216 Issues: 0 Forks: 11
https://github.com/SqueezeAILab/LLMCompiler
LLMCompiler: An LLM Compiler for Parallel Function Calling
Language: Python
#efficient_inference #function_calling #large_language_models #llama #llama2 #llm #llm_agent #llm_agents #llm_framework #llms #natural_language_processing #nlp #parallel_function_call #transformer
Stars: 216 Issues: 0 Forks: 11
https://github.com/SqueezeAILab/LLMCompiler
GitHub
GitHub - SqueezeAILab/LLMCompiler: [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling - SqueezeAILab/LLMCompiler
open-compass/MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
Language: Python
#llm #mistral #moe
Stars: 251 Issues: 6 Forks: 21
https://github.com/open-compass/MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
Language: Python
#llm #mistral #moe
Stars: 251 Issues: 6 Forks: 21
https://github.com/open-compass/MixtralKit
GitHub
GitHub - open-compass/MixtralKit: A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI - open-compass/MixtralKit
Writesonic/GPTRouter
Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability.
Language: TypeScript
#anthropic #azure_openai #cohere #google_gemini #langchain #llama_index #llm #llmops #llms #mlops #openai #palm_api
Stars: 130 Issues: 6 Forks: 16
https://github.com/Writesonic/GPTRouter
Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability.
Language: TypeScript
#anthropic #azure_openai #cohere #google_gemini #langchain #llama_index #llm #llmops #llms #mlops #openai #palm_api
Stars: 130 Issues: 6 Forks: 16
https://github.com/Writesonic/GPTRouter
GitHub
GitHub - Writesonic/GPTRouter: Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed…
Smoothly Manage Multiple LLMs (OpenAI, Anthropic, Azure) and Image Models (Dall-E, SDXL), Speed Up Responses, and Ensure Non-Stop Reliability. - Writesonic/GPTRouter