10 actions in 7 pieces of software · ranked by words, meaning and measured trust · 608 ms
- 1openthaigpt1.5-72b-instructdemo or tutorialno passport yet
modelrecord135 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- tool-calling
Can call tools (function calling).
- text->text
Takes text; returns text.
- structured-outputs
Can return JSON matching a schema.
- tool-calling
modelrecord
- llama3-70b-instruct
Task: Llama3-70b-instruct
- llama3
Task: llama3
- llama3-70b-instruct
modelrecord
- joehoover/falcon-40b-instruct
A 40 billion parameter language model trained to follow human instructions.
- joehoover/falcon-40b-instruct
modelrecord
- lucataco/upstage-llama-2-70b-instruct-v2
Upstage/Llama-2-70B-instruct-v2 - GPTQ
- lucataco/upstage-llama-2-70b-instruct-v2
modelrecord
- deepseek-ai/deepseek-math-7b-instruct
Pushing the Limits of Mathematical Reasoning in Open Language Models - Instruct model
- deepseek-ai/deepseek-math-7b-instruct
modelrecord
- automotive-/-transportation
Task: Automotive / Transportation
- automotive-/-transportation
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.