fix(docs): don't refer to meta/llama-3.1-8b-instruct from build.nvidia.com (#630)

marta-sd · web-flow · commit ed2b4b0440a8 · 2026-01-13T12:38:22.000+01:00
Signed-off-by: Marta Stepniewska-Dziubinska &lt;martas@nvidia.com&gt;
diff --git a/docs/about/concepts/_snippets/processed_results.json b/docs/about/concepts/_snippets/processed_results.json
@@ -3,7 +3,7 @@
   "benchmarks": {
     "ifeval": {
       "models": {
-        "meta/llama-3.1-8b-instruct": [
+        "meta/llama-3.2-3b-instruct": [
           {
             "invocation_id": "30500ae952e1eeab",
             "job_id": "30500ae952e1eeab.0",
@@ -23,7 +23,7 @@
     },
     "gpqa_diamond": {
       "models": {
-        "meta/llama-3.1-8b-instruct": [
+        "meta/llama-3.2-3b-instruct": [
           {
             "invocation_id": "30500ae952e1eeab",
             "job_id": "30500ae952e1eeab.1",
@@ -40,7 +40,7 @@
     },
     "mbpp": {
       "models": {
-        "meta/llama-3.1-8b-instruct": [
+        "meta/llama-3.2-3b-instruct": [
           {
             "invocation_id": "30500ae952e1eeab",
             "job_id": "30500ae952e1eeab.2",
diff --git a/docs/about/concepts/_snippets/results.yaml b/docs/about/concepts/_snippets/results.yaml
@@ -1,7 +1,7 @@
 # This is an exemplar result generated from the command described in the quickstart tutorial,
 # with limited samples for faster execution.
 
-command: 'export API_KEY=$API_KEY &&   simple_evals --model meta/llama-3.1-8b-instruct
+command: 'export API_KEY=$API_KEY &&   simple_evals --model meta/llama-3.2-3b-instruct
   --eval_name gpqa_diamond --url https://integrate.api.nvidia.com/v1/chat/completions
   --temperature 0.0 --top_p 1e-05 --max_tokens 4096 --out_dir /results/gpqa_diamond
   --cache_dir /results/gpqa_diamond/cache --num_threads 1 --max_retries 5 --timeout
@@ -82,7 +82,7 @@ target:
         name: post_eval_report
       tracking_requests_stats: true
     api_key: API_KEY
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     stream: null
     type: chat
     url: https://integrate.api.nvidia.com/v1/chat/completions
diff --git a/docs/deployment/bring-your-own-endpoint/hosted-services.md b/docs/deployment/bring-your-own-endpoint/hosted-services.md
@@ -49,7 +49,7 @@ defaults:
 target:
   api_endpoint:
     url: https://integrate.api.nvidia.com/v1/chat/completions
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     api_key_name: NGC_API_KEY  # Name of environment variable
 
 execution:
@@ -70,7 +70,7 @@ For multi-model comparison, run separate evaluations for each model and compare
 # Evaluate first model
 nemo-evaluator-launcher run \
     --config packages/nemo-evaluator-launcher/examples/local_basic.yaml \
-    -o target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o execution.output_dir=./results/llama-3.1-8b
 
 # Evaluate second model
diff --git a/docs/deployment/launcher-orchestrated/local.md b/docs/deployment/launcher-orchestrated/local.md
@@ -42,7 +42,7 @@ execution:
 
 target:
   api_endpoint:
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     url: https://integrate.api.nvidia.com/v1/chat/completions
     api_key_name: NGC_API_KEY
 
diff --git a/docs/evaluation/benchmarks/about.md b/docs/evaluation/benchmarks/about.md
@@ -113,7 +113,7 @@ export HF_TOKEN=hf_...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
@@ -166,7 +166,7 @@ export NGC_API_KEY=nvapi-...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
@@ -216,7 +216,7 @@ export HF_TOKEN=hf_...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
@@ -269,7 +269,7 @@ export NGC_API_KEY=nvapi-...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
@@ -319,7 +319,7 @@ export NGC_API_KEY=nvapi-...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
@@ -364,7 +364,7 @@ export NGC_API_KEY=nvapi-...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
diff --git a/docs/evaluation/index.md b/docs/evaluation/index.md
@@ -64,7 +64,7 @@ export NGC_API_KEY=nvapi-...
 nemo-evaluator-launcher run \
     --config ./config.yml \
     -o execution.output_dir=results \
-    -o +target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o +target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o +target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
     -o +target.api_endpoint.api_key_name=NGC_API_KEY
 ```
diff --git a/docs/evaluation/run-evals/code-generation.md b/docs/evaluation/run-evals/code-generation.md
@@ -80,7 +80,7 @@ eval_config = EvaluationConfig(
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.nvidia.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct", 
+        model_id="meta/llama-3.2-3b-instruct", 
         type=EndpointType.CHAT,
         api_key="your_api_key"
     )
@@ -107,7 +107,7 @@ export MY_API_KEY=your_api_key_here
 # Run code generation evaluation
 nemo-evaluator run_eval \
     --eval_type mbpp \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name MY_API_KEY \
@@ -210,7 +210,7 @@ from nemo_evaluator.api.api_dataclasses import (
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.nvidia.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct", 
+        model_id="meta/llama-3.2-3b-instruct", 
         type=EndpointType.CHAT,
         api_key="your_api_key"
     )
diff --git a/docs/evaluation/run-evals/function-calling.md b/docs/evaluation/run-evals/function-calling.md
@@ -78,7 +78,7 @@ eval_config = EvaluationConfig(
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.nvidia.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct", 
+        model_id="meta/llama-3.2-3b-instruct", 
         type=EndpointType.CHAT,
         api_key="your_api_key"
     )
@@ -104,7 +104,7 @@ export MY_API_KEY=your_api_key_here
 # Run function calling evaluation
 nemo-evaluator run_eval \
     --eval_type bfclv3_ast_prompting \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name MY_API_KEY \
diff --git a/docs/evaluation/run-evals/text-gen.md b/docs/evaluation/run-evals/text-gen.md
@@ -83,7 +83,7 @@ export NGC_API_KEY=nvapi-your-token-here  # API Key with access to build.nvidia.
 # Run evaluation
 nemo-evaluator run_eval \
     --eval_type gpqa_diamond \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name NGC_API_KEY \
@@ -106,7 +106,7 @@ from nemo_evaluator.api.api_dataclasses import (
 api_endpoint = ApiEndpoint(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
     type=EndpointType.CHAT,
-    model_id="meta/llama-3.1-8b-instruct",
+    model_id="meta/llama-3.2-3b-instruct",
     api_key="NGC_API_KEY"  # variable name storing the key
 )
 target = EvaluationTarget(api_endpoint=api_endpoint)
diff --git a/docs/get-started/_snippets/container_run.sh b/docs/get-started/_snippets/container_run.sh
@@ -14,7 +14,7 @@ docker run --rm --gpus all \
     nemo-evaluator run_eval \
         --eval_type mmlu_pro \
         --model_url https://integrate.api.nvidia.com/v1/chat/completions \
-        --model_id meta/llama-3.1-8b-instruct \
+        --model_id meta/llama-3.2-3b-instruct \
         --api_key_name MY_API_KEY \
         --output_dir /workspace/results
 # [snippet-end]
diff --git a/docs/get-started/_snippets/core_basic.py b/docs/get-started/_snippets/core_basic.py
@@ -43,7 +43,7 @@
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.nvidia.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct",
+        model_id="meta/llama-3.2-3b-instruct",
         api_key="NGC_API_KEY",
         type=EndpointType.CHAT,
     )
diff --git a/docs/get-started/_snippets/core_full_cli.sh b/docs/get-started/_snippets/core_full_cli.sh
@@ -7,7 +7,7 @@ Basic NeMo Evaluator Core CLI quickstart example.
 
 nemo-evaluator run_eval \
     --eval_type mmlu_pro \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name NGC_API_KEY \  # pass variable name not the key itself
diff --git a/docs/get-started/_snippets/core_full_example.py b/docs/get-started/_snippets/core_full_example.py
@@ -45,7 +45,7 @@
 # Configure target
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
-        model_id="meta/llama-3.1-8b-instruct",
+        model_id="meta/llama-3.2-3b-instruct",
         url="https://integrate.api.nvidia.com/v1/chat/completions",
         type=EndpointType.CHAT,
         api_key="NGC_API_KEY",
diff --git a/docs/get-started/_snippets/core_multi_benchmark.py b/docs/get-started/_snippets/core_multi_benchmark.py
@@ -33,7 +33,7 @@
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.nvidia.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct",
+        model_id="meta/llama-3.2-3b-instruct",
         api_key="NGC_API_KEY",
         type=EndpointType.CHAT,
     )
diff --git a/docs/get-started/_snippets/launcher_full_example.sh b/docs/get-started/_snippets/launcher_full_example.sh
@@ -10,7 +10,7 @@ export NGC_API_KEY="${NGC_API_KEY:-nvapi-your-key-here}"
 nemo-evaluator-launcher run \
     --config packages/nemo-evaluator-launcher/examples/local_basic.yaml \
     -o target.api_endpoint.url=https://integrate.api.nvidia.com/v1/chat/completions \
-    -o target.api_endpoint.model_id=meta/llama-3.1-8b-instruct \
+    -o target.api_endpoint.model_id=meta/llama-3.2-3b-instruct \
     -o target.api_endpoint.api_key_name=NGC_API_KEY \
     -o execution.output_dir=./results
 # [snippet-end]
diff --git a/docs/get-started/install.md b/docs/get-started/install.md
@@ -120,7 +120,7 @@ docker run --rm \
     nemo-evaluator run_eval \
         --eval_type mmlu_pro \
         --model_url https://integrate.api.nvidia.com/v1/chat/completions \
-        --model_id meta/llama-3.1-8b-instruct \
+        --model_id meta/llama-3.2-3b-instruct \
         --api_key_name NGC_API_KEY \
         --output_dir /workspace/results
 ```
diff --git a/docs/get-started/quickstart/container.md b/docs/get-started/quickstart/container.md
@@ -26,7 +26,7 @@ export HF_TOKEN=hf_your-token-here  # If using gated datasets
 # 4. Run evaluation
 nemo-evaluator run_eval \
     --eval_type mmlu_pro \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name NGC_API_KEY \
@@ -54,7 +54,7 @@ docker run --rm -it \
 # 3. Inside container - run evaluation
 nemo-evaluator run_eval \
     --eval_type mmlu_pro \
-    --model_id meta/llama-3.1-8b-instruct \
+    --model_id meta/llama-3.2-3b-instruct \
     --model_url https://integrate.api.nvidia.com/v1/chat/completions \
     --model_type chat \
     --api_key_name NGC_API_KEY \
@@ -82,7 +82,7 @@ docker run --rm \
         --eval_type mmlu_pro \
         --model_url https://integrate.api.nvidia.com/v1/chat/completions \
         --model_type chat \
-        --model_id meta/llama-3.1-8b-instruct \
+        --model_id meta/llama-3.2-3b-instruct \
         --api_key_name NGC_API_KEY \
         --output_dir /workspace/results
 ```
@@ -136,7 +136,7 @@ services:
     command: |
       nemo-evaluator run_eval 
         --eval_type mmlu_pro 
-        --model_id meta/llama-3.1-8b-instruct 
+        --model_id meta/llama-3.2-3b-instruct 
         --model_url https://integrate.api.nvidia.com/v1/chat/completions 
         --model_type chat 
         --api_key_name MY_API_KEY 
@@ -163,7 +163,7 @@ for benchmark in "${BENCHMARKS[@]}"; do
         nvcr.io/nvidia/eval-factory/simple-evals:{{ docker_compose_latest }} \
         nemo-evaluator run_eval \
             --eval_type $benchmark \
-            --model_id meta/llama-3.1-8b-instruct \
+            --model_id meta/llama-3.2-3b-instruct \
             --model_url https://integrate.api.nvidia.com/v1/chat/completions \
             --model_type chat \
             --api_key_name MY_API_KEY \
diff --git a/docs/get-started/quickstart/index.md b/docs/get-started/quickstart/index.md
@@ -144,7 +144,7 @@ curl -X POST "https://integrate.api.nvidia.com/v1/chat/completions" \
     -H "Authorization: Bearer $NGC_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
-        "model": "meta/llama-3.1-8b-instruct",
+        "model": "meta/llama-3.2-3b-instruct",
         "messages": [{"role": "user", "content": "Hello!"}],
         "max_tokens": 10
     }'
diff --git a/docs/libraries/nemo-evaluator-launcher/configuration/deployment/none.md b/docs/libraries/nemo-evaluator-launcher/configuration/deployment/none.md
@@ -53,7 +53,7 @@ execution:
 
 target:
   api_endpoint:
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     url: https://integrate.api.nvidia.com/v1/chat/completions
     api_key_name: NGC_API_KEY
 
@@ -138,7 +138,7 @@ execution:
 
 target:
   api_endpoint:
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     url: https://integrate.api.nvidia.com/v1/chat/completions
     api_key_name: NGC_API_KEY # API Key with access to build.nvidia.com
 
diff --git a/docs/libraries/nemo-evaluator-launcher/configuration/index.md b/docs/libraries/nemo-evaluator-launcher/configuration/index.md
@@ -35,7 +35,7 @@ execution:
 
 target:                  # Required for deployment: none
   api_endpoint:
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     url: https://integrate.api.nvidia.com/v1/chat/completions
     api_key_name: NGC_API_KEY
 
diff --git a/docs/libraries/nemo-evaluator-launcher/exporters/mlflow.md b/docs/libraries/nemo-evaluator-launcher/exporters/mlflow.md
@@ -66,7 +66,7 @@ export:
 
 target:
   api_endpoint:
-    model_id: meta/llama-3.1-8b-instruct
+    model_id: meta/llama-3.2-3b-instruct
     url: https://integrate.api.nvidia.com/v1/chat/completions
 
 evaluation:
diff --git a/docs/libraries/nemo-evaluator/api.md b/docs/libraries/nemo-evaluator/api.md
@@ -39,7 +39,7 @@ def run_eval() -> None:
     
     CLI Arguments:
         --eval_type: Type of evaluation to run (such as "mmlu_pro", "gpqa_diamond")
-        --model_id: Model identifier (such as "meta/llama-3.1-8b-instruct")
+        --model_id: Model identifier (such as "meta/llama-3.2-3b-instruct")
         --model_url: API endpoint URL (such as "https://integrate.api.NVIDIA.com/v1/chat/completions" for chat endpoint type)
         --model_type: Endpoint type ("chat", "completions", "vlm", "embedding")
         --api_key_name: Environment variable name for API key integration with endpoints (optional)
@@ -108,7 +108,7 @@ eval_config = EvaluationConfig(
 target_config = EvaluationTarget(
     api_endpoint=ApiEndpoint(
         url="https://integrate.api.NVIDIA.com/v1/chat/completions",
-        model_id="meta/llama-3.1-8b-instruct",
+        model_id="meta/llama-3.2-3b-instruct",
         type="chat",
         api_key="MY_API_KEY" # Name of the environment variable that stores api_key
     )
diff --git a/docs/libraries/nemo-evaluator/workflows/cli.md b/docs/libraries/nemo-evaluator/workflows/cli.md
diff --git a/docs/libraries/nemo-evaluator/workflows/python-api.md b/docs/libraries/nemo-evaluator/workflows/python-api.md
diff --git a/docs/references/api/nemo-evaluator-launcher/api.md b/docs/references/api/nemo-evaluator-launcher/api.md
diff --git a/docs/references/api/nemo-evaluator/api/index.rst b/docs/references/api/nemo-evaluator/api/index.rst
diff --git a/docs/references/api/nemo-evaluator/cli.md b/docs/references/api/nemo-evaluator/cli.md
diff --git a/docs/references/faq.md b/docs/references/faq.md
diff --git a/docs/tutorials/create-framework-definition-file.md b/docs/tutorials/create-framework-definition-file.md
diff --git a/docs/tutorials/local-evaluation-of-existing-endpoint.md b/docs/tutorials/local-evaluation-of-existing-endpoint.md
diff --git a/packages/nemo-evaluator-launcher/examples/local_auto_export.yaml b/packages/nemo-evaluator-launcher/examples/local_auto_export.yaml
diff --git a/packages/nemo-evaluator-launcher/examples/local_basic.yaml b/packages/nemo-evaluator-launcher/examples/local_basic.yaml
diff --git a/packages/nemo-evaluator-launcher/examples/notebooks/nemo-evaluator-launcher-api.ipynb b/packages/nemo-evaluator-launcher/examples/notebooks/nemo-evaluator-launcher-api.ipynb
