mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-20 15:33:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

feat: add LM Studio JIT load mode

Browse source
This commit is contained in:
Marcelo 2026-06-08 15:46:38 -03:00 • committed by kshitij
parent e844ea9f0b
commit 1a323d608e
4 changed files with 101 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

14
website/docs/integrations/providers.md
View file

@ -844,7 +844,7 @@ hermes model
# If LM Studio server auth is enabled, enter LM_API_KEY when prompted
```
Hermes will automatically load a LM Studio model with 64K context length
By default, Hermes explicitly asks LM Studio to load the selected model with 64K context length before the first request.
To change context length in LM Studio:
@ -860,6 +860,18 @@ You can use the CLI to estimate if the model will fit: `lms load model-name --co
To set persistent per-model defaults: My Models tab → gear icon on the model → set context size.
:::
If you use LM Studio's Just-In-Time loading / Auto-Evict feature and want LM Studio to manage model loading and eviction from normal chat requests, skip Hermes' explicit preload step:
```bash
hermes config set model.lmstudio_load_mode jit
```
Set it back to the default explicit preload behavior with:
```bash
hermes config set model.lmstudio_load_mode explicit
```
**Tool calling:** Supported since LM Studio 0.3.6. Models with native tool-calling training (Qwen 2.5, Llama 3.x, Mistral, Hermes) are auto-detected and shown with a tool badge. Other models use a generic fallback that may be less reliable.
---