README.md

metadata

license: mit
tags:
  - mergekit
  - merge
base_model:
  - meta-llama/Llama-2-70b-hf
  - codellama/CodeLlama-70b-Python-hf
  - codellama/CodeLlama-70b-Instruct-hf
model-index:
  - name: code-llama-70b-python-instruct
    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: 29.61
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          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: 25.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          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: 23.5
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          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: 49.26
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          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: 49.25
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          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: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NobodyExistsOnTheInternet/code-llama-70b-python-instruct
          name: Open LLM Leaderboard

Codellama-python-instruct

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using meta-llama/Llama-2-70b-hf as a base.

Models Merged

The following models were included in the merge:

• codellama/CodeLlama-70b-Python-hf
• codellama/CodeLlama-70b-Instruct-hf

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: codellama/CodeLlama-70b-Python-hf
    parameters:
      density: 0.5
      weight: 0.5
  - model: codellama/CodeLlama-70b-Instruct-hf
    parameters:
      density: 0.5
      weight: 1.0
merge_method: dare_ties
base_model: meta-llama/Llama-2-70b-hf
parameters:
  # You can uncomment and set these parameters as needed
  # normalize: false
  # int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.55
AI2 Reasoning Challenge (25-Shot)	29.61
HellaSwag (10-Shot)	25.66
MMLU (5-Shot)	23.50
TruthfulQA (0-shot)	49.26
Winogrande (5-shot)	49.25
GSM8k (5-shot)	0.00