Search
alpaca-lora
 - Instruct-tune LLaMA on consumer hardware.
...moretrlx
 - A repo for distributed training of language models with Reinforcement Learning via Human Feedback. (RLHF)
...moregoogle-deepmind/gemma
 - Open weights LLM from Google DeepMind.
...moreOpenAssistant SFT 6
30 billion LLaMa-based model made by HuggingFace for the chatting conversation.
Vicuna Delta v0
An open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
Falcon 7B
A 7B parameters causal decoder-only model built by TII and trained on 1,500B tokens of RefinedWeb enhanced with curated corpora.
...moreIntroducing Gemma 3: The most capable model you can run on a single GPU or TPU
LLM application: Introducing Gemma 3: The most capable model you can run on a single GPU or TPU
Phi-2: The surprising power of small language models
LLM application: Phi-2: The surprising power of small language models
StackLLaMA: A hands-on guide to train LLaMA with RLHF
LLM application: StackLLaMA: A hands-on guide to train LLaMA with RLHF
PaLM2
LLM application: PaLM2
PaLM2 and Future work: Gemini model
LLM application: PaLM2 and Future work: Gemini model
Discord Community
SuperAgent ecosystem: Discord Community
HuggingFace Models
SuperAgent ecosystem: HuggingFace Models
Twitter/X
SuperAgent ecosystem: Twitter/X
C# API reference
Semantic Kernel ecosystem: C# API reference
Python API reference
Semantic Kernel ecosystem: Python API reference
Haystack Enterprise: Support & Platform
Haystack ecosystem: Haystack Enterprise: Support & Platform
Telemetry
Haystack ecosystem: Telemetry
Contributing to Haystack
Haystack ecosystem: Contributing to Haystack
Organizations using Haystack
Haystack ecosystem: Organizations using Haystack