10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 584 ms
modelrecord30,656 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord71,896 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- meta/meta-llama-3-8b-instruct
An 8 billion parameter language model from Meta, fine tuned for chat completions
- meta/meta-llama-3-8b-instruct
modelrecord
- llama3-8b-instruct
Task: Llama3-8b-instruct
- llama3-8b-instruct
modelrecord
- llama3.1
Task: Llama3.1
- llama3.1-8b-instruct
Task: Llama3.1-8b-instruct
- llama3.1
modelrecord
- text->text
Takes text; returns text.
- text->text
- 7aeroforgefound in code, not yet checkedno passport yet
MCP servergodlydonuts/aeroforge
- llama-3.1-8b-instruct-awq
Quantized (int4) generative text model with 8 billion parameters from Meta.
- llama-3-8b-instruct-awq
Quantized (int4) generative text model with 8 billion parameters from Meta.
- llama-3.1-8b-instruct-awq
modelrecord
- llama-3-sqlcoder-8b-instruct
Task: Llama-3-SQLCoder-8B-Instruct
- llama-3-sqlcoder-8b-instruct
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.