GGUF
•
llama
A fine-tune of Meta's Llama 3.1, Hermes is further trained on hand-curated datasets as well and synthetic data. Excels in dialogue and code generation.
Model info
Model
Hermes 3 Llama 3.1 8B
Author
NousResearch
Repository
Arch
llama
Parameters
8B
Format
gguf
Size on disk
about 4.92 GB
Download the model using lms
— LM Studio's developer CLI.
lms get hermes-3-8b
curl http://localhost:1234/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "hermes-3-8b",
"messages": [
{ "role": "system", "content": "Always answer in rhymes." },
{ "role": "user", "content": "Introduce yourself." }
],
"temperature": 0.7,
"max_tokens": -1,
"stream": true
}'
lms log stream
to see your prompts as they are sent to the LLM.lmstudio.js
- LM Studio SDK documentation (TypeScript)lms log stream
- Stream server logslms
- LM Studio's CLI documentation