README.md

---
license: cc-by-nc-4.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
- tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
pipeline_tag: text-generation
model-index:
- name: llama-3-Nephilim-v3-8B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 41.74
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 28.96
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 9.14
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 6.04
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 8.33
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 29.02
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=grimjim/llama-3-Nephilim-v3-8B
      name: Open LLM Leaderboard
---
# llama-3-Nephilim-v3-8B

This repo contains a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

GGUF quants are [here](https://huggingface.co/grimjim/llama-3-Nephilim-v3-8B-GGUF).

Although none of the components of this merge were trained for roleplay nor intended for it, the model can be used effectively in that role.

Tested with temperature 1 and minP 0.01. This model leans toward being creative, so adjust temperature upward or downward as desired.

There are initial format consistency issues with the merged model, but this can be mitigated in an Instruct prompt. Additionally, promptsteering was employed to vary the text generation output to avoid some of the common failings observed during text generation with Llama 3 8B models. The complete Instruct prompt used during testing is available below.

- [context template](https://huggingface.co/debased-ai/SillyTavern-settings/blob/main/advanced_formatting/context_template/Llama%203%20Instruct%20Immersed2.json)
- [instruct prompt](https://huggingface.co/debased-ai/SillyTavern-settings/blob/main/advanced_formatting/instruct_mode/Llama%203%20Instruct%20Immersed2.json)

Built with Meta Llama 3.

## Merge Details
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge](https://huggingface.co/grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge) as a base.

### Models Merged

The following models were included in the merge:
* [tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 32]
    model: grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
  - layer_range: [0, 32]
    model: tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
    parameters:
      weight: 0.1

```

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_grimjim__llama-3-Nephilim-v3-8B)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |20.54|
|IFEval (0-Shot)    |41.74|
|BBH (3-Shot)       |28.96|
|MATH Lvl 5 (4-Shot)| 9.14|
|GPQA (0-shot)      | 6.04|
|MuSR (0-shot)      | 8.33|
|MMLU-PRO (5-shot)  |29.02|