README.md

---
license: other
metrics:
- accuracy
base_model: Mihaiii/Pallas-0.5
inference: false
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
model-index:
- name: Pallas-0.5-frankenmerge
  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: 61.77
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      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: 80.36
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      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: 67.62
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      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: 54.07
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      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: 77.74
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      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: 24.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Mihaiii/Pallas-0.5-frankenmerge
      name: Open LLM Leaderboard
---

This is a frankenmerge of [Mihaiii/Pallas-0.5](https://huggingface.co/Mihaiii/Pallas-0.5) .
It was done using [mergekit](https://github.com/cg123/mergekit).

It works well with long system prompts.

It isn't generic in a sense that it shouldn't be used for story telling, for example, but only for reasoning and text comprehension.

This model is trained on a private dataset.

# Prompt Format:

```
SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT:
```

Merge config:
```yaml
slices:
  - sources:
    - model: "Mihaiii/Pallas-0.5"
      layer_range: [0, 60]
  - sources:
    - model: "Mihaiii/Pallas-0.5"
      layer_range: [58, 60]
  - sources:
    - model: "Mihaiii/Pallas-0.5"
      layer_range: [55, 56]
merge_method: passthrough
dtype: bfloat16
```

Quants:

[TheBloke/Pallas-0.5-frankenmerge-GGUF](https://huggingface.co/TheBloke/Pallas-0.5-frankenmerge-GGUF)

[TheBloke/Pallas-0.5-frankenmerge-GPTQ](https://huggingface.co/TheBloke/Pallas-0.5-frankenmerge-GPTQ)

[TheBloke/Pallas-0.5-frankenmerge-AWQ](https://huggingface.co/TheBloke/Pallas-0.5-frankenmerge-AWQ)

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Mihaiii__Pallas-0.5-frankenmerge)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |60.95|
|AI2 Reasoning Challenge (25-Shot)|61.77|
|HellaSwag (10-Shot)              |80.36|
|MMLU (5-Shot)                    |67.62|
|TruthfulQA (0-shot)              |54.07|
|Winogrande (5-shot)              |77.74|
|GSM8k (5-shot)                   |24.11|