Hugging Face's logo

ibm-fms
/
llama-13b-accelerator

Transformers
Safetensors
mlp_speculator
Inference Endpoints
Model card Files Community
1
JRosenkranz commited on
Commit
cfc7388
•
1 Parent(s): 8e6cadf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -143,7 +143,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
143
  --speculator_path=ibm-fms/llama-13b-accelerator \
144
  --speculator_source=hf \
145
  --speculator_variant=840m \
146
- --compile \
147
  ```
148
 
149
  ##### batch_size=4 (compile)
@@ -159,5 +159,5 @@ python fms-extras/scripts/paged_speculative_inference.py \
159
  --speculator_source=hf \
160
  --speculator_variant=840m \
161
  --batch_input \
162
- --compile \
163
  ```
 
143
  --speculator_path=ibm-fms/llama-13b-accelerator \
144
  --speculator_source=hf \
145
  --speculator_variant=840m \
146
+ --compile
147
  ```
148
 
149
  ##### batch_size=4 (compile)
 
159
  --speculator_source=hf \
160
  --speculator_variant=840m \
161
  --batch_input \
162
+ --compile
163
  ```