Update README.md

README.md

@@ -108,7 +108,7 @@ _Note: first prompt may be slower as there is a slight warmup time_
 #### Install
 
 ```bash
-git clone --branch ibm_7b_instruct_lab_variant --single-branch https://github.com/JRosenkranz/fms-extras.git
+git clone https://github.com/foundation-model-stack/fms-extras
 (cd fms-extras && pip install -e .)
 pip install transformers==4.35.0 sentencepiece numpy
 ```
@@ -126,7 +126,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
     --tokenizer=$MODEL_PATH \
     --speculator_path=ibm/granite-7b-lab-accelerator \
     --speculator_source=hf \
-    --speculator_variant=1.4b \
+    --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \
     --compile \
     --compile_mode=reduce-overhead
@@ -143,7 +143,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
     --tokenizer=$MODEL_PATH \
     --speculator_path=ibm/granite-7b-lab-accelerator \
     --speculator_source=hf \
-    --speculator_variant=1.4b \
+    --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \
     --compile \
 ```
@@ -159,7 +159,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
     --tokenizer=$MODEL_PATH \
     --speculator_path=ibm/granite-7b-lab-accelerator \
     --speculator_source=hf \
-    --speculator_variant=1.4b \
+    --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \
     --batch_input \
     --compile \