---
license: cc-by-nc-4.0
tags:
- merge
model-index:
- name: Nyxene-11B
  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: 68.34
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      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: 84.54
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      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: 65.09
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      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: 57.5
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      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: 79.08
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      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: 51.78
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/Nyxene-11B
      name: Open LLM Leaderboard
---

## Description

This repo contains bf16 files of Nyxene-11B. Like [OmniMix](https://huggingface.co./Undi95/Mistral-11B-OmniMix) but with new models.

## Model used
- [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co./berkeley-nest/Starling-LM-7B-alpha)
- [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co./mlabonne/NeuralHermes-2.5-Mistral-7B)
- [fblgit/juanako-7b-UNA](https://huggingface.co./fblgit/juanako-7b-UNA)
- [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co./ehartford/dolphin-2.1-mistral-7b)



## Prompt template

The best one after further testing is this one:

```
<|system|>
Below is an instruction that describes a task. Write a response that appropriately completes the request.
<|user|>
{prompt}
<|assistant|>
```

## The secret sauce

dolphin-juanako-11B :
```
slices:
  - sources:
    - model: fblgit/juanako-7b-UNA
      layer_range: [0, 24]
  - sources:
    - model: ehartford/dolphin-2.1-mistral-7b
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```

Starling-NeuralHermes-11B :
```
slices:
  - sources:
    - model: berkeley-nest/Starling-LM-7B-alpha
      layer_range: [0, 24]
  - sources:
    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```

Nyxene-11B :
```
slices:
  - sources:
      - model: dolphin-juanako-11B
        layer_range: [0, 48]
      - model: Starling-NeuralHermes-11B
        layer_range: [0, 48]
merge_method: slerp
base_model: dolphin-juanako-11B
parameters:
  t:
    - filter: lm_head 
      value: [0.75]
    - filter: embed_tokens
      value: [0.75]
    - filter: self_attn
      value: [0.75, 0.25]
    - filter: mlp
      value:  [0.25, 0.75]
    - filter: layernorm
      value: [0.5, 0.5]
    - filter: modelnorm
      value: [0.75]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16
```
I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here.

# [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_beberik__Nyxene-11B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |67.72|
|AI2 Reasoning Challenge (25-Shot)|68.34|
|HellaSwag (10-Shot)              |84.54|
|MMLU (5-Shot)                    |65.09|
|TruthfulQA (0-shot)              |57.50|
|Winogrande (5-shot)              |79.08|
|GSM8k (5-shot)                   |51.78|