ibm-fms
/

llama-13b-accelerator

Inference Endpoints

Model card Files Files and versions Community

JRosenkranz commited on Apr 21

Commit

0c7b651

•

1 Parent(s): 8c8a362

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -91,7 +91,7 @@ pip install transformers==4.35.0 sentencepiece numpy
 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
-    --model_path=/path/to/model_weights/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \
@@ -105,7 +105,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
-    --model_path=/path/to/model_weights/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \
@@ -118,7 +118,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
-    --model_path=/path/to/model_weights/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \

 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
+    --model_path=/path/to/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \
 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
+    --model_path=/path/to/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \
 ```bash
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=13b \
+    --model_path=/path/to/llama/13B-F \
     --model_source=hf \
     --tokenizer=/path/to/llama/13B-F \
     --speculator_path=ibm-fms/llama-13b-accelerator \