mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-03 02:11:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

group size 1 works, some timeouts but could be just local server

Browse source
This commit is contained in:
Shannon Sands 2026-02-03 16:24:47 +10:00
parent 30221d8c20
commit 6cb4fe948a
3 changed files with 40 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.env.example
View file

@ -28,6 +28,10 @@ HERMES_BACKEND=openai
# ATROPOS_TOKENIZER_NAME=NousResearch/Hermes-4.3-36B
# ATROPOS_SERVER_API_KEY=local
#
# If you plan to run GRPO-style group sampling (e.g. `--env.group_size 4`) against
# llama.cpp, start the server with at least that many slots, e.g.:
# LLAMA_CPP_PARALLEL=4 Hermes-Agent/scripts/launch_llama_cpp_hermes_4_36b.sh
#
# Generic OpenAI-compatible (base URL should include /v1):
# OPENAI_BASE_URL=http://127.0.0.1:8080/v1
# OPENAI_API_KEY=local