metadata

license: llama3
library_name: transformers
tags:
  - mergekit
  - merge
  - not-for-all-audiences
base_model:
  - Hastagaras/Halu-8B-Llama3-v0.3
  - Blackroot/Llama-3-LongStory-LORA
  - Hastagaras/Halu-8B-Llama3-v0.3
  - Blackroot/Llama-3-8B-Abomination-LORA
  - Hastagaras/Halu-8B-Llama3-v0.3
model-index:
  - name: Halu-8B-Llama3-Blackroot
    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: 63.82
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          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: 84.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          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: 67.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          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: 53.28
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          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: 79.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          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: 70.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Hastagaras/Halu-8B-Llama3-Blackroot
          name: Open LLM Leaderboard

EXPERIMENTAL MODEL

VERY IMPORTANT: This model has not been extensively tested or evaluated, and its performance characteristics are currently unknown. It may generate harmful, biased, or inappropriate content. Please exercise caution and use it at your own risk and discretion.

I just tried saishf's merged model, and it's great. So I decided to try a similar merge method with Blackroot's LoRA that I had found earlier.

I don't know what to say about this model... this model is very strange...Maybe because Blackroot's amazing Loras used human data and not synthetic data, hence the model turned out to be very human-like...even the actions or narrations.

WARNING: This model is very unsafe in certain parts...especially in RP.

IMATRIX GGUF IS HERE made available by Lewdiculous

STATIC GGUF IS HERE made avaible by mradermacher

Merge Method

This model was merged using the Model Stock merge method using Hastagaras/Halu-8B-Llama3-v0.3 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-LongStory-LORA
  - model: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-8B-Abomination-LORA
merge_method: model_stock
base_model: Hastagaras/Halu-8B-Llama3-v0.3
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.78
AI2 Reasoning Challenge (25-Shot)	63.82
HellaSwag (10-Shot)	84.55
MMLU (5-Shot)	67.04
TruthfulQA (0-shot)	53.28
Winogrande (5-shot)	79.48
GSM8k (5-shot)	70.51