527 2 weeks ago

Trained for hermes agent

tools thinking
ollama run gurubot/Carnice-27b-GGUF:Q4_K_M

Details

2 weeks ago

8d9e34b0f0ee · 17GB ·

qwen35
·
26.9B
·
Q4_K_M
{{ .Prompt }}
{ "presence_penalty": 1.5, "temperature": 1, "top_k": 20, "top_p": 0.95 }

Readme

image.png

Carnice-27b is the merged full-model release of the Trinity Hermes-Agent training run on top of Qwen/Qwen3.5-27B.

Trained using traces from lambda/hermes-agent-reasoning-traces

Carnice-27b is tuned for Hermes-Agent style terminal, file, browser, repo, debugging, and multi-step tool workflows.

source https://huggingface.co/kai-os/Carnice-27b