thuannh commited on
Commit
17452cc
·
verified ·
1 Parent(s): 49bec78

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -52,13 +52,12 @@ vllm serve Menlo/Lucy-128k \
52
  --host 0.0.0.0 \
53
  --port 1234 \
54
  --enable-auto-tool-choice \
55
- --tool-call-parser hermes \
56
- --rope-scaling '{"rope_type":"yarn","factor":3.2,"original_max_position_embeddings":40960}' --max-model-len 131072
57
  ```
58
 
59
  Or `llama-server` from `llama.cpp`:
60
  ```bash
61
- llama-server ... --rope-scaling yarn --rope-scale 3.2 --yarn-orig-ctx 40960
62
  ```
63
 
64
  ### Recommended Sampling Parameters
 
52
  --host 0.0.0.0 \
53
  --port 1234 \
54
  --enable-auto-tool-choice \
55
+ --tool-call-parser hermes
 
56
  ```
57
 
58
  Or `llama-server` from `llama.cpp`:
59
  ```bash
60
+ llama-server ...
61
  ```
62
 
63
  ### Recommended Sampling Parameters