Can't access meta-llama/Llama-2-7b using llmstudio cli tool

[sunilswain]

Hey
I've trying to use llmstudio cli since I do not have enough resources required by the H2o llmstudio. So I use Kaggle to run my cli tool.
But anyways, I'm trying to train Llama-2-7b on my own dataset, and it gives me this error

Cannot access gated repo for url https://huggingface.co/meta-llama/Llama-2-7b/resolve/main/config.json.
Access to model meta-llama/Llama-2-7b is restricted. You must be authenticated to access it.
all done

I know I do have access to this repo. I want to know, how can I authenticate myself while I'm using llmstudio?

Thanks

this is my config.yaml

architecture:
    backbone_dtype: int8
    force_embedding_gradients: false
    gradient_checkpointing: true
    intermediate_dropout: 0.0
    pretrained: true
    pretrained_weights: ''
augmentation:
    neftune_noise_alpha: 0.0
    random_parent_probability: 0.0
    skip_parent_probability: 0.0
    token_mask_probability: 0.0
dataset:
    add_eos_token_to_answer: true
    add_eos_token_to_prompt: true
    add_eos_token_to_system: true
    answer_column: output_prompt
    chatbot_author: DataTeam
    chatbot_name: EsspLGPT
    data_sample: 1.0
    data_sample_choice:
    - Train
    - Validation
    limit_chained_samples: true
    mask_prompt_labels: true
    parent_id_column: None
    personalize: False
    prompt_column:
    - input_prompt
    system_column: None
    text_answer_separator: <|answer|>
    text_prompt_start: <|prompt|>
    text_system_start: <|system|>
    train_dataframe: data/EssplTravelPolicyQA/qa_train.csv
    validation_dataframe: data/EssplTravelPolicyQA/qa_val.csv
    validation_size: 0.01
    validation_strategy: automatic
environment:
    compile_model: false
    deepspeed_allgather_bucket_size: 1000000
    deepspeed_method: ZeRO2
    deepspeed_reduce_bucket_size: 1000000
    deepspeed_stage3_param_persistence_threshold: 1000000
    deepspeed_stage3_prefetch_bucket_size: 1000000
    find_unused_parameters: false
    gpus:
    - '0'
    - '1'
    huggingface_branch: main
    mixed_precision: false
    number_of_workers: 1
    seed: -1
    trust_remote_code: false
    use_deepspeed: false
experiment_name: EssplTravelPolicyFT
llm_backbone: meta-llama/Llama-2-7b
logging:
    logger: None
    neptune_project: Zoo/h2o-llm
output_directory: EssplTravelPolicyFTExperiment
prediction:
    batch_size_inference: 0
    do_sample: false
    max_length_inference: 256
    max_time: 120.0
    metric: BLEU
    metric_gpt_model: gpt-3.5-turbo-0301
    metric_gpt_template: general
    min_length_inference: 2
    num_beams: 1
    num_history: 4
    repetition_penalty: 1.1
    stop_tokens: ''
    temperature: 0.0
    top_k: 0
    top_p: 1.0
problem_type: text_causal_language_modeling
tokenizer:
    add_prompt_answer_tokens: false
    max_length: 1072
    max_length_answer: 512
    max_length_prompt: 1600
    padding_quantile: 1.0
    use_fast: true
training:
    batch_size: 2
    differential_learning_rate: 1.0e-05
    differential_learning_rate_layers: []
    drop_last_batch: true
    epochs: 1
    evaluate_before_training: false
    evaluation_epochs: 1.0
    grad_accumulation: 1
    gradient_clip: 0.0
    learning_rate: 0.0001
    lora: true
    lora_alpha: 16
    lora_dropout: 0.05
    lora_r: 4
    lora_target_modules: ''
    loss_function: TokenAveragedCrossEntropy
    optimizer: AdamW
    save_best_checkpoint: false
    schedule: Cosine
    train_validation_data: false
    use_flash_attention_2: false
    warmup_epochs: 0.1
    weight_decay: 0.0

[pascal-pfeiffer]

In the UI, the huggingface key can be provided in the settings to automatically authenticate with huggingface hub.
For CLI users, please download gated or private models ahead of running the experiment using e.g. Huggingface CLI or python API: https://huggingface.co/docs/huggingface_hub/guides/cli, https://huggingface.co/docs/huggingface_hub/guides/download