README.md

metadata

language:
  - en
license: mit
datasets:
  - vibhorag101/phr_mental_therapy_dataset
  - jerryjalapeno/nart-100k-synthetic
pipeline_tag: text-generation
model-index:
  - name: llama-2-13b-chat-hf-phr_mental_therapy
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 38.82
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 72.76
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 23.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 46.92
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 65.59
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 7.81
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vibhorag101/llama-2-13b-chat-hf-phr_mental_therapy
          name: Open LLM Leaderboard

Model Card

• This model is a finetune of the llama-2-13b-chat-hf model on a therapy dataset.
• The model aims to provide basic therapy to the users and improve their mental health until they seek professional help.
• The model has been adjusted to encourage giving cheerful responses to the user. The system prompt has been mentioned below.

Model Details

Training Hardware

• RTX A5000 24GB
• 48 Core Intel Xeon
• 128GB Ram.

Model Hyperparameters

• This training script was used to do the finetuning.
• The shareGPT format dataset was converted to llama-2 training format using this script.
• num_train_epochs = 2
• per_device_train_batch_size = 2
• per_device_eval_batch_size = 2
• gradient_accumulation_steps = 1
• max_seq_length = 4096
• lora_r = 64
• lora_alpha = 16
• lora_dropout = 0.1
• use_4bit = True
• bnb_4bit_compute_dtype = "float16"
• bnb_4bit_quant_type = "nf4"
• use_nested_quant = False
• fp16 = False
• bf16 = True
• Data Sample: 1000 (80:20 split)

Model System Prompt

You are a helpful and joyous mental therapy assistant. Always answer as helpfully and cheerfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

Model Training Data

Model Benchmarks

Detailed results can be found here

Metric	Value
Avg.	42.5
ARC (25-shot)	38.82
HellaSwag (10-shot)	72.76
MMLU (5-shot)	23.12
TruthfulQA (0-shot)	46.92
Winogrande (5-shot)	65.59
GSM8K (5-shot)	7.81

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	42.50
AI2 Reasoning Challenge (25-Shot)	38.82
HellaSwag (10-Shot)	72.76
MMLU (5-Shot)	23.12
TruthfulQA (0-shot)	46.92
Winogrande (5-shot)	65.59
GSM8k (5-shot)	7.81