RichardErkhov/nlpguy_-_ColorShadow-7B-v2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ColorShadow-7B-v2 - GGUF

• —Model creator: https://huggingface.co/nlpguy/
• —Original model: https://huggingface.co/nlpguy/ColorShadow-7B-v2/

Original model description: --- license: apache-2.0 tags:

• —merge model-index:
• —name: ColorShadow-7B-v2 results:
• —task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2arc config: ARC-Challenge split: test args: numfew_shot: 25 metrics:
• —type: accnorm value: 67.15 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: numfewshot: 10 metrics:
• —type: accnorm value: 84.69 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: numfewshot: 5 metrics:
• —type: acc value: 60.34 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthfulqa config: multiplechoice split: validation args: numfewshot: 0 metrics:
• —type: mc2 value: 62.93 source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winograndexl split: validation args: numfew_shot: 5 metrics:
• —type: acc value: 78.85 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: numfewshot: 5 metrics:
• —type: acc value: 47.31 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=nlpguy/ColorShadow-7B-v2 name: Open LLM Leaderboard ---

ColorShadow-7B-v2

This is a Gradient-SLERP merge between diffnamehard/Mistral-CatMacaroni-slerp-7B and cookinai/Valkyrie-V1 performed using mergekit.

Here is the config file used:

  slices:
    - sources:
        - model: diffnamehard/Mistral-CatMacaroni-slerp-7B
          layer_range: [0, 32]
        - model: cookinai/Valkyrie-V1
          layer_range: [0, 32]
  merge_method: slerp
  base_model: diffnamehard/Mistral-CatMacaroni-slerp-7B
  parameters:
    t:
      - filter: self_attn
        value: [1, 0.5, 0.7, 0.3, 0]
      - filter: mlp
        value: [0, 0.5, 0.3, 0.7, 1]
      - value: 0.5 # fallback for rest of tensors
  dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here