Updates HF model_ids and readmes for 3.1

recipes/3p_integrations/lamini/text2sql_memory_tuning/meta_lamini.ipynb

@@ -145,7 +145,7 @@
     "class Args:\n",
     "    def __init__(self, \n",
     "                 max_examples=100, \n",
-    "                 sql_model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\", \n",
+    "                 sql_model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\", \n",
     "                 gold_file_name=\"gold-test-set.jsonl\",\n",
     "                 training_file_name=\"generated_queries.jsonl\",\n",
     "                 num_to_generate=10):\n",
@@ -197,7 +197,7 @@
     }
    ],
    "source": [
-    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "question = \"\"\"Who is the highest paid NBA player?\"\"\"\n",
     "system = f\"\"\"You are an NBA analyst with 15 years of experience writing complex SQL queries. Consider the nba_roster table with the following schema:\n",
@@ -418,7 +418,7 @@
     "class ScoreStage(GenerationNode):\n",
     "    def __init__(self):\n",
     "        super().__init__(\n",
-    "            model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
+    "            model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
     "            max_new_tokens=150,\n",
     "        )\n",
     "\n",
@@ -712,7 +712,7 @@
     "class ModelStage(GenerationNode):\n",
     "    def __init__(self):\n",
     "        super().__init__(\n",
-    "            model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
+    "            model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
     "            max_new_tokens=300,\n",
     "        )\n",
     "\n",
@@ -808,7 +808,7 @@
     "class QuestionStage(GenerationNode):\n",
     "    def __init__(self):\n",
     "        super().__init__(\n",
-    "            model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
+    "            model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
     "            max_new_tokens=150,\n",
     "        )\n",
     "\n",
@@ -1055,7 +1055,7 @@
    ],
    "source": [
     "args = Args()\n",
-    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "dataset = get_dataset(args, make_question)\n",
     "finetune_args = get_default_finetune_args()\n",
@@ -1601,7 +1601,7 @@
    ],
    "source": [
     "args = Args(training_file_name=\"archive/generated_queries_large_filtered_cleaned.jsonl\")\n",
-    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "dataset = get_dataset(args, make_question)\n",
     "finetune_args = get_default_finetune_args()\n",
@@ -1798,7 +1798,7 @@
    ],
    "source": [
     "args = Args(training_file_name=\"generated_queries_v2.jsonl\")\n",
-    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "dataset = get_dataset(args, make_question)\n",
     "finetune_args = get_default_finetune_args()\n",
@@ -1966,7 +1966,7 @@
    ],
    "source": [
     "args = Args(training_file_name=\"archive/generated_queries_v2_large_filtered_cleaned.jsonl\")\n",
-    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+    "llm = lamini.Lamini(model_name=\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "dataset = get_dataset(args, make_question)\n",
     "finetune_args = get_default_finetune_args()\n",

recipes/3p_integrations/lamini/text2sql_memory_tuning/util/parse_arguments.py

@@ -16,7 +16,7 @@ def parse_arguments():
     parser.add_argument(
         "--sql-model-name",
         type=str,
-        default="meta-llama/Meta-Llama-3-8B-Instruct",
+        default="meta-llama/Meta-Llama-3.1-8B-Instruct",
         help="The model to use for text2sql",
         required=False,
     )

recipes/3p_integrations/llama_on_prem.md

@@ -8,7 +8,7 @@ We'll use the Amazon EC2 instance running Ubuntu with an A10G 24GB GPU as an exa
 
 The Colab notebook to connect via LangChain with Llama 3 hosted as the vLLM and TGI API services is [here](https://colab.research.google.com/drive/1rYWLdgTGIU1yCHmRpAOB2D-84fPzmOJg), also shown in the sections below.
 
-This tutorial assumes that you you have been granted access to the Meta Llama 3 on Hugging Face - you can open a Hugging Face Meta model page [here](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) to confirm that you see "Gated model You have been granted access to this model"; if you see "You need to agree to share your contact information to access this model", simply complete and submit the form in the page.
+This tutorial assumes that you you have been granted access to the Meta Llama 3 on Hugging Face - you can open a Hugging Face Meta model page [here](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) to confirm that you see "Gated model You have been granted access to this model"; if you see "You need to agree to share your contact information to access this model", simply complete and submit the form in the page.
 
 You'll also need your Hugging Face access token which you can get at your Settings page [here](https://huggingface.co/settings/tokens).
 
@@ -33,7 +33,7 @@ There are two ways to deploy Llama 3 via vLLM, as a general API server or an Ope
 Run the command below to deploy vLLM as a general Llama 3 service:
 
 ```
-python -m vllm.entrypoints.api_server --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3-8B-Instruct
+python -m vllm.entrypoints.api_server --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3.1-8B-Instruct
 ```
 
 Then on another terminal you can run:
@@ -68,13 +68,13 @@ Also, if you have multiple GPUs, you can add the `--tensor-parallel-size` argume
 git clone https://github.com/vllm-project/vllm
 cd vllm/vllm/entrypoints
 conda activate llama3
-python api_server.py --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3-8B-Instruct --tensor-parallel-size 4
+python api_server.py --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3.1-8B-Instruct --tensor-parallel-size 4
 ```
 
 With multiple GPUs, you can also run replica of models as long as your model size can fit into targeted GPU memory. For example, if you have two A10G with 24 GB memory, you can run two Llama 3 8B models at the same time. This can be done by launching two api servers each targeting specific CUDA cores on different ports:
-`CUDA_VISIBLE_DEVICES=0 python api_server.py --host 0.0.0.0 --port 5000  --model meta-llama/Meta-Llama-3-8B-Instruct`
+`CUDA_VISIBLE_DEVICES=0 python api_server.py --host 0.0.0.0 --port 5000  --model meta-llama/Meta-Llama-3.1-8B-Instruct`
 and
-`CUDA_VISIBLE_DEVICES=1 python api_server.py --host 0.0.0.0 --port 5001  --model meta-llama/Meta-Llama-3-8B-Instruct`
+`CUDA_VISIBLE_DEVICES=1 python api_server.py --host 0.0.0.0 --port 5001  --model meta-llama/Meta-Llama-3.1-8B-Instruct`
 The benefit would be that you can balance incoming requests to both models, reaching higher batch size processing for a trade-off of generation latency.
 
 
@@ -83,14 +83,14 @@ The benefit would be that you can balance incoming requests to both models, reac
 You can also deploy the vLLM hosted Llama 3 as an OpenAI-Compatible service to easily replace code using OpenAI API. First, run the command below:
 
 ```
-python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3-8B-Instruct
+python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 5000 --model meta-llama/Meta-Llama-3.1-8B-Instruct
 ```
 
 Then on another terminal, run:
 
 ```
 curl http://localhost:5000/v1/completions -H "Content-Type: application/json" -d '{
-        "model": "meta-llama/Meta-Llama-3-8B-Instruct",
+        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
         "prompt": "Who wrote the book Innovators dilemma?",
         "max_tokens": 300,
         "temperature": 0
@@ -118,7 +118,7 @@ from langchain.llms import VLLMOpenAI
 llm = VLLMOpenAI(
     openai_api_key="EMPTY",
     openai_api_base="http://<vllm_server_ip_address>:5000/v1",
-    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    model_name="meta-llama/Meta-Llama-3.1-8B-Instruct",
 )
 
 print(llm("Who wrote the book godfather?"))
@@ -136,7 +136,7 @@ You can now use the Llama 3 instance `llm` created this way in any of the demo a
 The easiest way to deploy Llama 3 with TGI is using its official docker image. First, replace `<your_hugging_face_access_token>` and set the three required shell variables (you may replace the `model` value above with another Llama 3 model):
 
 ```
-model=meta-llama/Meta-Llama-3-8B-Instruct
+model=meta-llama/Meta-Llama-3.1-8B-Instruct
 volume=$PWD/data
 token=<your_hugging_face_access_token>
 ```

recipes/quickstart/Running_Llama3_Anywhere/Running_Llama_on_HF_transformers.ipynb

@@ -92,7 +92,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Then, we will set the model variable to a specific model we’d like to use. In this demo, we will use the 8b chat model `meta-llama/Meta-Llama-3-8B-Instruct`. Using Meta models from Hugging Face requires you to\n",
+    "Then, we will set the model variable to a specific model we’d like to use. In this demo, we will use the 8b chat model `meta-llama/Meta-Llama-3.1-8B-Instruct`. Using Meta models from Hugging Face requires you to\n",
     "\n",
     "1. Accept Terms of Service for Meta Llama 3 on Meta [website](https://llama.meta.com/llama-downloads).\n",
     "2. Use the same email address from Step (1) to login into Hugging Face.\n",
@@ -125,7 +125,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = \"meta-llama/Meta-Llama-3-8B-Instruct\"\n",
+    "model = \"meta-llama/Meta-Llama-3.1-8B-Instruct\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model)"
    ]
   },

recipes/quickstart/finetuning/quickstart_peft_finetuning.ipynb

@@ -90,7 +90,7 @@
     "from llama_recipes.configs import train_config as TRAIN_CONFIG\n",
     "\n",
     "train_config = TRAIN_CONFIG()\n",
-    "train_config.model_name = \"meta-llama/Meta-Llama-3-8B\"\n",
+    "train_config.model_name = \"meta-llama/Meta-Llama-3.1-8B\"\n",
     "train_config.num_epochs = 1\n",
     "train_config.run_validation = False\n",
     "train_config.gradient_accumulation_steps = 4\n",

recipes/responsible_ai/prompt_guard/Prompt Guard Tutorial.ipynb

@@ -55,7 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "prompt_injection_model_name = 'meta-llama/PromptGuard'\n",
+    "prompt_injection_model_name = 'meta-llama/Prompt-Guard-86M'\n",
     "tokenizer = AutoTokenizer.from_pretrained(prompt_injection_model_name)\n",
     "model = AutoModelForSequenceClassification.from_pretrained(prompt_injection_model_name)"
    ]

recipes/responsible_ai/prompt_guard/inference.py

@@ -11,12 +11,12 @@ Utilities for loading the PromptGuard model and evaluating text for jailbreaks a
 """
 
 
-def load_model_and_tokenizer(model_name='meta-llama/PromptGuard'):
+def load_model_and_tokenizer(model_name='meta-llama/Prompt-Guard-86M'):
     """
     Load the PromptGuard model from Hugging Face or a local model.
     
     Args:
-        model_name (str): The name of the model to load. Default is 'meta-llama/PromptGuard'.
+        model_name (str): The name of the model to load. Default is 'meta-llama/Prompt-Guard-86M'.
         
     Returns:
         transformers.PreTrainedModel: The loaded model.

recipes/use_cases/customerservice_chatbots/RAG_chatbot/RAG_Chatbot_Example.ipynb

@@ -418,7 +418,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model=meta-llama/Meta-Llama-3-8B-Instruct\n",
+    "model=meta-llama/Meta-Llama-3.1-8B-Instruct\n",
     "volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run\n",
     "token=#your-huggingface-token\n",
     "docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:2.0 --model-id $model"

recipes/use_cases/customerservice_chatbots/RAG_chatbot/vectorstore/mongodb/rag_mongodb_llama3_huggingface_open_source.ipynb

@@ -934,11 +934,11 @@
       "source": [
         "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
         "import torch\n",
-        "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
         "# CPU Enabled uncomment below 👇🏽\n",
-        "# model = AutoModelForCausalLM.from_pretrained(\"meta-llama/Meta-Llama-3-8B-Instruct\")\n",
+        "# model = AutoModelForCausalLM.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
         "# GPU Enabled use below 👇🏽\n",
-        "model = AutoModelForCausalLM.from_pretrained(\"meta-llama/Meta-Llama-3-8B-Instruct\", torch_dtype=torch.bfloat16, device_map=\"auto\")"
+        "model = AutoModelForCausalLM.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\", torch_dtype=torch.bfloat16, device_map=\"auto\")"
       ]
     },
     {

src/llama_recipes/inference/safety_utils.py

@@ -160,7 +160,7 @@ class LlamaGuardSafetyChecker(object):
         from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
         from llama_recipes.inference.prompt_format_utils import build_default_prompt, create_conversation, LlamaGuardVersion
 
-        model_id = "meta-llama/LlamaGuard-7b"
+        model_id = "meta-llama/Llama-Guard-3-8B"
 
         quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 

src/llama_recipes/tools/README.md

@@ -7,7 +7,7 @@ This is the reverse conversion for `convert_llama_weights_to_hf.py` script from
 - Copy file params.json from the official llama download into that directory.
 - Run the conversion script. `model-path` can be a Hugging Face hub model or a local hf model directory.
 ```
-python -m llama_recipes.tools.convert_hf_weights_to_llama --model-path meta-llama/Meta-Llama-3-70B-Instruct --output-dir test70B --model-size 70B
+python -m llama_recipes.tools.convert_hf_weights_to_llama --model-path meta-llama/Meta-Llama-3.1-70B-Instruct --output-dir test70B --model-size 70B
 ```
 
 ## Step 1: Run inference

src/tests/conftest.py

@@ -6,7 +6,7 @@ import pytest
 from transformers import AutoTokenizer
 
 ACCESS_ERROR_MSG = "Could not access tokenizer at 'meta-llama/Llama-2-7b-hf'. Did you log into huggingface hub and provided the correct token?"
-LLAMA_VERSIONS = ["meta-llama/Llama-2-7b-hf", "meta-llama/Meta-Llama-3-8B"]
+LLAMA_VERSIONS = ["meta-llama/Llama-2-7b-hf", "meta-llama/Meta-Llama-3.1-8B"]
 
 @pytest.fixture(params=LLAMA_VERSIONS)
 def llama_version(request):

src/tests/datasets/test_custom_dataset.py

@@ -11,7 +11,7 @@ EXPECTED_RESULTS={
         "example_1": "[INST] Who made Berlin [/INST] dunno",
         "example_2": "[INST] Quiero preparar una pizza de pepperoni, puedes darme los pasos para hacerla? [/INST] Claro!",
     },
-    "meta-llama/Meta-Llama-3-8B":{
+    "meta-llama/Meta-Llama-3.1-8B":{
         "example_1": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nWho made Berlin<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\ndunno<|eot_id|><|end_of_text|>",
         "example_2": "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHow to start learning guitar and become a master at it?",
     },

src/tests/datasets/test_grammar_datasets.py

@@ -10,7 +10,7 @@ EXPECTED_RESULTS = {
         "label": 1152,
         "pos": 31,
     },
-    "meta-llama/Meta-Llama-3-8B":{
+    "meta-llama/Meta-Llama-3.1-8B":{
         "label": 40,
         "pos": 26,
     },

src/tests/datasets/test_samsum_datasets.py

@@ -10,7 +10,7 @@ EXPECTED_RESULTS = {
         "label": 8432,
         "pos": 242,
     },
-    "meta-llama/Meta-Llama-3-8B":{
+    "meta-llama/Meta-Llama-3.1-8B":{
         "label": 2250,
         "pos": 211,
     },

src/tests/test_batching.py

@@ -9,7 +9,7 @@ EXPECTED_SAMPLE_NUMBER ={
         "train": 96,
         "eval": 42,
     },
-    "meta-llama/Meta-Llama-3-8B": {
+    "meta-llama/Meta-Llama-3.1-8B": {
         "train": 79,
         "eval": 34,
     }

tools/benchmarks/inference/on_prem/README.md

@@ -17,8 +17,8 @@ For example, we have an instance from Azure that has 8xA100 80G GPUs, and we wan
 
 Here are examples for deploying 2x70B chat models over 8 GPUs with vLLM.
 ```
-CUDA_VISIBLE_DEVICES=0,1,2,3 python -m vllm.entrypoints.openai.api_server  --model meta-llama/Meta-Llama-3-70B-Instruct --tensor-parallel-size 4 --disable-log-requests --port 8000
-CUDA_VISIBLE_DEVICES=4,5,6,7 python -m vllm.entrypoints.openai.api_server  --model meta-llama/Meta-Llama-3-70B-Instruct --tensor-parallel-size 4 --disable-log-requests --port 8001
+CUDA_VISIBLE_DEVICES=0,1,2,3 python -m vllm.entrypoints.openai.api_server  --model meta-llama/Meta-Llama-3.1-70B-Instruct --tensor-parallel-size 4 --disable-log-requests --port 8000
+CUDA_VISIBLE_DEVICES=4,5,6,7 python -m vllm.entrypoints.openai.api_server  --model meta-llama/Meta-Llama-3.1-70B-Instruct --tensor-parallel-size 4 --disable-log-requests --port 8001
 ```
 Once you have finished deployment, you can use the command below to run benchmark scripts in a separate terminal.
 

tools/benchmarks/llm_eval_harness/README.md

@@ -39,7 +39,7 @@ pip install -e .
 To run evaluation for Hugging Face `Llama3 8B` model  on a single GPU please run the following,
 
 ```bash
-python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3-8B --tasks hellaswag --device cuda:0   --batch_size 8
+python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3.1-8B --tasks hellaswag --device cuda:0   --batch_size 8
 
 ```
 Tasks can be extended by using `,` between them for example `--tasks hellaswag,arc`.
@@ -51,7 +51,7 @@ To set the number of shots you can use `--num_fewshot` to set the number for few
 In case you have fine-tuned your model using PEFT you can set the PATH to the PEFT checkpoints using PEFT as part of model_args as shown below:
 
 ```bash
-python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3-8B, dtype="float",peft=../peft_output --tasks hellaswag --num_fewshot 10  --device cuda:0 --batch_size 8
+python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3.1-8B, dtype="float",peft=../peft_output --tasks hellaswag --num_fewshot 10  --device cuda:0 --batch_size 8
 ```
 
 ### Limit the number of examples in benchmarks
@@ -59,7 +59,7 @@ python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3-8B, dt
 There has been an study from [IBM on efficient benchmarking of LLMs](https://arxiv.org/pdf/2308.11696.pdf), with main take a way that to identify if a model is performing poorly, benchmarking on wider range of tasks is more important than the number example in each task. This means you could run the evaluation harness with fewer number of example to have initial decision if the performance got worse from the base line. To limit the number of example here, it can be set using `--limit` flag with actual desired number. But for the full assessment you would need to run the full evaluation. Please read more in the paper linked above.
 
 ```bash
-python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3-8B,dtype="float",peft=../peft_output --tasks hellaswag --num_fewshot 10  --device cuda:0 --batch_size 8 --limit 100
+python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3.1-8B,dtype="float",peft=../peft_output --tasks hellaswag --num_fewshot 10  --device cuda:0 --batch_size 8 --limit 100
 ```
 
 ### Reproducing Hugging Face Open-LLM-Leaderboard
@@ -76,7 +76,7 @@ bash open_llm_eval_prep.sh
 Now we can run the eval benchmark:
 
 ```bash
-python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3-8B,dtype="float",peft=../peft_output --num_fewshot 10  --device cuda:0 --batch_size 8 --limit 100 --open_llm_leaderboard_tasks
+python eval.py --model hf --model_args pretrained=meta-llama/Meta-Llama-3.1-8B,dtype="float",peft=../peft_output --num_fewshot 10  --device cuda:0 --batch_size 8 --limit 100 --open_llm_leaderboard_tasks
 ```
 
 In the HF leaderboard, the [LLMs are evaluated on 7 benchmarks](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) from Language Model Evaluation Harness as described below:
@@ -107,7 +107,7 @@ To perform *data-parallel evaluation* (where each GPU loads a **separate full co
 ```bash
 accelerate config
 
-accelerate launch eval.py --model hf --model_args "pretrained=meta-llama/Meta-Llama-3-8B" --limit 100 --open-llm-leaderboard-tasks --output_path ./results.json --log_samples
+accelerate launch eval.py --model hf --model_args "pretrained=meta-llama/Meta-Llama-3.1-8B" --limit 100 --open-llm-leaderboard-tasks --output_path ./results.json --log_samples
 ```
 
 In case your model can fit on a single GPU, this allows you to evaluate on K GPUs K times faster than on one.
@@ -119,7 +119,7 @@ In case your model is *too large to fit on a single GPU.*
 In this setting, run the library *outside of the `accelerate` launcher*, but passing `parallelize=True` to `--model_args` as follows:
 
 ```bash
-python eval.py --model hf --model_args "pretrained=meta-llama/Meta-Llama-3-8B,parallelize=True" --limit 100 --open_llm_leaderboard_tasks --output_path ./results.json --log_samples
+python eval.py --model hf --model_args "pretrained=meta-llama/Meta-Llama-3.1-8B,parallelize=True" --limit 100 --open_llm_leaderboard_tasks --output_path ./results.json --log_samples
 ```
 
 
@@ -138,7 +138,7 @@ These two options (`accelerate launch` and `parallelize=True`) are mutually excl
 Also `lm-evaluation-harness` supports vLLM for faster inference on [supported model types](https://docs.vllm.ai/en/latest/models/supported_models.html), especially faster when splitting a model across multiple GPUs. For single-GPU or multi-GPU — tensor parallel, data parallel, or a combination of both — inference, for example:
 
 ```bash
-python eval.py --model vllm --model_args "pretrained=meta-llama/Meta-Llama-3-8B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8,data_parallel_size=2" --limit 100 --open_llm_leaderboard_tasks --output_path ./results.json --log_samples --batch_size auto
+python eval.py --model vllm --model_args "pretrained=meta-llama/Meta-Llama-3.1-8B,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.8,data_parallel_size=2" --limit 100 --open_llm_leaderboard_tasks --output_path ./results.json --log_samples --batch_size auto
 ```
 For a full list of supported vLLM configurations, please to [here](https://github.com/EleutherAI/lm-evaluation-harness/blob/076372ee9ee81e25c4e2061256400570354a8d1a/lm_eval/models/vllm_causallms.py#L44-L62).