README.md

---
license: apache-2.0
tags:
- merge
- mergekit
model-index:
- name: tinyllama_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: 30.2
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_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: 51.01
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_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: 26.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_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: 40.18
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_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: 58.72
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_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: 1.59
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=bn22/tinyllama_frankenmerge
      name: Open LLM Leaderboard
---

# tinyllama_frankenmerge

This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):
 * [TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
 * [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T)

## 🧩 Configuration

```yml
slices:
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
      layer_range: [0, 16]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [6, 22]
merge_method: passthrough
dtype: float16
```
# [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_bn22__tinyllama_frankenmerge)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |34.64|
|AI2 Reasoning Challenge (25-Shot)|30.20|
|HellaSwag (10-Shot)              |51.01|
|MMLU (5-Shot)                    |26.11|
|TruthfulQA (0-shot)              |40.18|
|Winogrande (5-shot)              |58.72|
|GSM8k (5-shot)                   | 1.59|