Update README.md

README.md

@@ -13,7 +13,7 @@ pip install -e .
 
 ## Description
 
-This model is intended to be used as an accelerator for [granite 7B (instruct lab)](https://huggingface.co/instructlab/granite-7b-lab) and takes inspiration 
+This model is intended to be used as an accelerator for [granite-7b-instruct](https://huggingface.co/ibm-granite/granite-7b-instruct) and takes inspiration 
 from the Medusa speculative decoding architecture. This accelerator modifies the MLP into a multi-stage MLP, where each stage predicts 
 a single token in the draft based on both a state vector and sampled token
 from the prior stage (the base model can be considered stage 0).
@@ -47,14 +47,14 @@ TGIS_IMAGE=quay.io/wxpe/text-gen-server:main.ddc56ee
 
 docker pull $TGIS_IMAGE
 
-# optionally download granite-7b-lab if the weights do not already exist
+# optionally download granite-7b-instruct if the weights do not already exist
 docker run --rm \
     -v $HF_HUB_CACHE:/models \
     -e HF_HUB_CACHE=/models \
     -e TRANSFORMERS_CACHE=/models \
     $TGIS_IMAGE \
     text-generation-server download-weights \
-    ibm-granite/granite-7b-lab \
+    ibm-granite/granite-7b-instruct \
     --token $HF_HUB_TOKEN
 
 # optionally download the speculator model if the weights do not already exist
@@ -64,7 +64,7 @@ docker run --rm \
     -e TRANSFORMERS_CACHE=/models \
     $TGIS_IMAGE \
     text-generation-server download-weights \
-    ibm-granite/granite-7b-lab-accelerator \
+    ibm-granite/granite-7b-instruct-accelerator \
     --token $HF_HUB_TOKEN
 
 # note: if the weights were downloaded separately (not with the above commands), please place them in the HF_HUB_CACHE directory and refer to them with /models/<model_name>
@@ -74,8 +74,8 @@ docker run -d --rm --gpus all \
     -v $HF_HUB_CACHE:/models \
     -e HF_HUB_CACHE=/models \
     -e TRANSFORMERS_CACHE=/models \
-    -e MODEL_NAME=ibm-granite/granite-7b-lab \
-    -e SPECULATOR_NAME=ibm-granite/granite-7b-lab-accelerator \
+    -e MODEL_NAME=ibm-granite/granite-7b-instruct \
+    -e SPECULATOR_NAME=ibm-granite/granite-7b-instruct-accelerator \
     -e FLASH_ATTENTION=true \
     -e PAGED_ATTENTION=true \
     -e DTYPE=float16 \
@@ -106,7 +106,7 @@ _Note: first prompt may be slower as there is a slight warmup time_
 #### start the server
 
 ```bash
-model=ibm-granite/granite-7b-lab-accelerator
+model=ibm-granite/granite-7b-instruct-accelerator
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:latest --model-id $model
 ```
@@ -139,13 +139,13 @@ pip install transformers==4.35.0 sentencepiece numpy
 ##### batch_size=1 (compile + cudagraphs)
 
 ```bash
-MODEL_PATH=/path/to/ibm-granite/granite-7b-lab
+MODEL_PATH=/path/to/ibm-granite/granite-7b-instruct
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=7b.ibm_instruct_lab \
     --model_path=$MODEL_PATH \
     --model_source=hf \
     --tokenizer=$MODEL_PATH \
-    --speculator_path=ibm-granite/granite-7b-lab-accelerator \
+    --speculator_path=ibm-granite/granite-7b-instruct-accelerator \
     --speculator_source=hf \
     --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \
@@ -156,13 +156,13 @@ python fms-extras/scripts/paged_speculative_inference.py \
 ##### batch_size=1 (compile)
 
 ```bash
-MODEL_PATH=/path/to/ibm-granite/granite-7b-lab
+MODEL_PATH=/path/to/ibm-granite/granite-7b-instruct
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=7b.ibm_instruct_lab \
     --model_path=$MODEL_PATH \
     --model_source=hf \
     --tokenizer=$MODEL_PATH \
-    --speculator_path=ibm-granite/granite-7b-lab-accelerator \
+    --speculator_path=ibm-granite/granite-7b-instruct-accelerator \
     --speculator_source=hf \
     --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \
@@ -172,13 +172,13 @@ python fms-extras/scripts/paged_speculative_inference.py \
 ##### batch_size=4 (compile)
 
 ```bash
-MODEL_PATH=/path/to/ibm-granite/granite-7b-lab
+MODEL_PATH=/path/to/ibm-granite/granite-7b-instruct
 python fms-extras/scripts/paged_speculative_inference.py \
     --variant=7b.ibm_instruct_lab \
     --model_path=$MODEL_PATH \
     --model_source=hf \
     --tokenizer=$MODEL_PATH \
-    --speculator_path=ibm-granite/granite-7b-lab-accelerator \
+    --speculator_path=ibm-granite/granite-7b-instruct-accelerator \
     --speculator_source=hf \
     --speculator_variant=1_4b \
     --top_k_tokens_per_head=4,3,2,2,2 \