Free Models

While paid models often provide superior performance and capabilities, there are also several free models available that can be used with ServerAssistantAI. Many of these models are open-source and can be a good starting point for servers.

Embedding Models

Embedding models are used to convert text data into numerical representations called embeddings. These embeddings capture the semantic meaning and relationships between different pieces of text, allowing the AI to find the most relevant context from the document.txt file when answering a question.

Provider	Model Name	MTEB	Embedding Dimensions
HuggingFace		64.68	1024
Cohere		64.47	1024
HuggingFace		64.41	1024
HuggingFace		64.23	1024
Cohere		64.01	1024

Large Language Models

Large Language Models (LLMs) are powerful AI models that can understand and generate human-like text based on the input they receive. In ServerAssistantAI, LLMs process the user's question along with the relevant context provided by the embedding model to generate accurate and context-aware responses.

Provider	Model Name	ELO	Speed (tokens per second)	Service uses responses to improve model?
Google-AIStudio		1268	57.2 TPS	Yes
Google-AIStudio		1232	133.3 TPS	Yes
Groq		1203	300+! TPS	No
Cohere		1188	43.16 TPS	No
Cohere		1149	94.52 TPS	No
HuggingFace	meta-llama/Meta-Llama-3-8B-Instruct	1147	N/A	No
HuggingFace	01-ai/Yi-1.5-34B-Chat	1116	N/A	No
HuggingFace	mistralai/Mixtral-8x7B-Instruct-v0.1	1114	N/A	No
HuggingFace	google/gemma-1.1-7b-it	1086	N/A	No
HuggingFace	NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO	1083	N/A	No
HuggingFace	mistralai/Mistral-7B-Instruct-v0.3	1074	N/A	No

Open-source free LLMs have a higher chance of hallucinating compared to paid models.

Model results were updated on 5/25/2024 using the following sources: | Source 1 | Source 2 | Source 3 | Source 4 |