Progress on hackathon automation and content

README.org

@@ -81,48 +81,58 @@ Once the cluster gpu machinepool has been created we need to deploy [[https://mi
 #+NAME: Install minio via oc
 #+begin_src tmux
 # Deploy minio
-oc new-project minio && oc --namespace minio apply -f setup/minio-setup.yaml
+oc new-project minio && oc --namespace minio apply --filename setup/minio-setup.yaml
 
 # Wait for minio to come up
 oc --namespace minio rollout status deployment/minio --watch
 #+end_src
 
 
-With minio deployed we need to create a bucket and upload some content to it.
+With minio deployed we need to create a bucket and upload some content to it to pre seed a model. We can do this by remotely executing minio cli `mc` commands within the `minio` pod.
 
 #+NAME: Configure minio via oc
 #+begin_src tmux
-oc get pods -n minio
-#+end_src
+# Retrieve the running minio pod
+pod=$(oc get pods --namespace "minio" --output name)
 
+# Retrieve the minio credentials
+minio_user=$(oc --namespace "minio" get secret "minio-secret" -o jsonpath='{.data.minio_root_user}' | base64 --decode)
+minio_pass=$(oc --namespace "minio" get secret "minio-secret" -o jsonpath='{.data.minio_root_password}' | base64 --decode)
 
-** Download model from huggingface into each `on prem` clusters Minio `model`'s bucket
+# Configure the minio cli alias
+oc --namespace "minio" exec "${pod}" -- mc alias set local http://localhost:9000 "${minio_user}" "${minio_pass}"
 
-#+begin_src tmux
-HUGGINGFACE_TOKEN="HUGGINGFACE_TOKEN"
-pip install --upgrade huggingface_hub
-huggingface-cli login --token "${HUGGINGFACE_TOKEN}"
-git clone https://huggingface.co/instructlab/granite-7b-lab
+# Make the models bucket
+oc --namespace "minio" exec "${pod}" -- mc mb "local/models"
 #+end_src
 
-or use this:
-https://github.com/tnscorcoran/rhods-finetunning-demo/blob/main/vllm_get_from_huggingface.ipynb
 
+** Populate minio bucket with model
 
-** Upload model to cluster minio
-Consider using this:
-https://github.com/tnscorcoran/rhods-finetunning-demo/blob/main/vllm_push_to_minio.ipynb
+With the bucket created we need to push some model content to it, we can do that with the magic of `git` and `mc`. We need to start by downloading the bucket content.
 
-TODO Run aws configure and pull values out of that automatically.
 
 #+begin_src tmux
-export AWS_ACCESS_KEY_ID=<placeholder>
-export AWS_SECRET_ACCESS_KEY=<placeholder>
-export AWS_DEFAULT_REGION=<placeholder>
-export AWS_S3_ENDPOINT=$(oc get route minio-api -o jsonpath='.spec.host')
-export AWS_S3_BUCKET="models"
-
-python3 setup/minio-upload.py
+pod=$(oc get pods --namespace "minio" --output name)
+oc --namespace "minio" exec "${pod}" -- mkdir /tmp/model --parent
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/added_tokens.json?download=true -o /tmp/model/added_tokens.json
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/config.json?download=true -o /tmp/model/config.json
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/generation_config.json?download=true -o /tmp/model/generation_config.json
+oc --namespace minio exec "${pod}" -- curl -L https://huggingface.co/instructlab/granite-7b-lab/resolve/main/model-00001-of-00003.safetensors?download=true -o /tmp/model/model-00001-of-00003.safetensors
+oc --namespace minio exec "${pod}" -- curl -L https://huggingface.co/instructlab/granite-7b-lab/resolve/main/model-00002-of-00003.safetensors?download=true -o /tmp/model/model-00002-of-00003.safetensors
+oc --namespace minio exec "${pod}" -- curl -L https://huggingface.co/instructlab/granite-7b-lab/resolve/main/model-00003-of-00003.safetensors?download=true -o /tmp/model/model-00003-of-00003.safetensors
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/model.safetensors.index.json?download=true -o /tmp/model/model.safetensors.index.json
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/special_tokens_map.json?download=true -o /tmp/model/special_tokens_map.json
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/tokenizer.json?download=true -o /tmp/model/tokenizer.json
+oc --namespace minio exec "${pod}" -- curl -L https://huggingface.co/instructlab/granite-7b-lab/resolve/main/tokenizer.model?download=true -o /tmp/model/tokenizer.model
+oc --namespace minio exec "${pod}" -- curl https://huggingface.co/instructlab/granite-7b-lab/resolve/main/tokenizer_config.json?download=true -o /tmp/model/tokenizer_config.json
 #+end_src
 
 
+#+begin_src tmux
+# Retreieve the pod name
+pod=$(oc get pods --namespace "minio" --output name)
+
+# Upload files via minio cli
+oc --namespace "minio" exec "${pod}" -- mc cp --recursive /tmp/model local/models/granite-7b-lab
+#+end_src

data/hackathon/scenario1.mdx

@@ -28,7 +28,7 @@ The bank is currently going through a "bake off" evaluating multiple options for
 
 Your hackathon team are the pre-sales technical team engaging with various ACME teams and leadership to try and win the bake off, securing buy-in for a large scale OpenShift AI deployment to proceed.
 
-We're chasing a $5 million AUD deal. Each of the challenges you complete during this hackathon will secure an $AUD portion of this deal. At your disposal is a very expensive OpenShift and OpenShift AI contractor - whose services come at a cost of $25,000 AUD per hour of engagement. You may engage them at various points throughout the challenges, but their costs will be deducted from the deal value you secure.
+We're chasing a `$5` million AUD deal. Each of the challenges you complete during this hackathon will secure an $AUD portion of this deal. At your disposal is a very expensive OpenShift and OpenShift AI contractor - whose services come at a cost of `$25,000` AUD per hour of engagement. You may engage them at various points throughout the challenges, but their costs will be deducted from the deal value you secure.
 
 The winner will be the team with the highest deal secured.
 
@@ -78,4 +78,4 @@ If you get stuck on a question, fear not, perhaps try a different approach. If y
 
 > [team name] are stuck on [exercise] and are engaging contractor support.
 
-A hackathon organiser will join your breakout room to put the expensive contractor to work (bear in mind it will cost $25k AUD!) 😂
+A hackathon organiser will join your breakout room to put the expensive contractor to work (bear in mind it will cost `$25k` AUD!) 😂