fix cicd ckpt conversion

Signed-off-by: Slyne Deng <[email protected]>
NVIDIA · Jul 10, 2024 · b0267df · b0267df
1 parent dfca213
commit b0267df
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 2 deletions.
diff --git a/examples/multimodal/multimodal_llm/neva/conf/vita_config.yaml b/examples/multimodal/multimodal_llm/neva/conf/vita_config.yaml
@@ -58,7 +58,7 @@ model:
   micro_batch_size: 1 # limited by GPU memory
   global_batch_size: 128 # will use more micro batches to reach global batch size
 
-  tensor_model_parallel_size: 4 # intra-layer model parallelism
+  tensor_model_parallel_size: 1 # intra-layer model parallelism
   pipeline_model_parallel_size: 1 # inter-layer model parallelism
   context_parallel_size: 1 # kqv model parallelism
   virtual_pipeline_model_parallel_size: null # interleaved pipeline

diff --git a/tutorials/multimodal/LITA Tutorial.ipynb b/tutorials/multimodal/LITA Tutorial.ipynb
@@ -145,6 +145,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "! cd /opt/\n",
     "! git clone --depth 1 --branch v1.2.2 https://github.com/haotian-liu/LLaVA/\n",
     "! export PYTHONPATH=/opt/LLaVA/:$PYTHONPATH\n",
     "! cd /ws  # do not run the below commands under `/opt` folder"
@@ -168,7 +169,7 @@
     "    --out-file /ws/converted_models/Llama-3-VILA1.5-8B.nemo \\\n",
     "    --tokenizer-model /ws/converted_models/tokenizer/ \\\n",
     "    --config-file vita_config.yaml \\\n",
-    "    --model-type VITA \\ \n",
+    "    --model-type VITA \\\n",
     "    --conv-template llama_3"
    ]
   },

diff --git a/tutorials/multimodal/images/LITA_arch.png b/tutorials/multimodal/images/LITA_arch.png