README.md

---
tags:
- merge
license: other
model-index:
- name: QuartetAnemoi-70B-t0.0001
  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: 73.38
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      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: 88.9
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      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: 75.42
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      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: 69.53
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      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: 85.32
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      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: 68.61
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alchemonaut/QuartetAnemoi-70B-t0.0001
      name: Open LLM Leaderboard
---

<img src=https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001/resolve/main/anemoi.png>

# QuartetAnemoi-70B-t0.0001

A sequential merge using a custom algorithm (NearSwap) of:
- [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
- [Sao10K/WinterGoddess-1.4x-70B-L2](https://huggingface.co/Sao10K/WinterGoddess-1.4x-70B-L2)
- [Aurora-Nights-70B-v1.0](https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0)
- [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1)

<br/>

In our testing, this model seems like a storyteller, as might be expected, but the changes from this merge are extremely soft. We were impressed that, unlike most models, at the end of a story it did not often use cliches such as "In the end", "And so", "beacon of hope", etc.

<br/>

This repo has the GGUF quants. Full weights are available at: [alchemonaut/QuartetAnemoi-70B-t0.0001](https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001)

<br/>
<br/>

# NearSwap Algorithm

NearSwap retains most of the weights of the base model (Miqu), but when a weight is similar between the two, it is interpolated to the secondary model value. A parameter *t* specifies the sameness threshold. When the distance between two values is below *t*, the weight from the secondary model is used.

This version of the model uses *t* = 0.0001. At this *t*, about 0.8% of weights are fully switched to the secondary model during each pass. Model quality rapidly degrades above *t* = 0.0025:

- *t* = 0.0001 (~0.8% full swap): This model
- *t* = 0.0003 (~2%  full swap)
- *t* = 0.001  (~10% full swap): [BoreanGale-70B](https://huggingface.co/alchemonaut/BoreanGale-70B)
- *t* = 0.0025 (~18% full swap): Generates one paragraph okay, but then reverts to garbage
- *t* = 0.005  (~35% full swap): Garbage; semi-related word lists
- *t* = 0.01   (~55% full swap): Garbage; pseudorandom tokens output

For QuartetAnemoi-70B-t0.0001, the three secondary models were each merged sequentially with *t* = 0.0001.

NearSwap implementation:
```
    t: Union[float, np.ndarray],
    v0: Union[np.ndarray, torch.Tensor],
    v1: Union[np.ndarray, torch.Tensor],
...
    lweight = numpy.absolute(v0-v1)
    lweight = t / lweight
    lweight = numpy.nan_to_num(lweight, nan=1.0, posinf=1.0, neginf=1.0)
    numpy.clip(lweight, a_min=0.0, a_max=1.0, out=lweight)
    res = lerp(lweight,v0,v1)
```
<br/>
<br/>


# License and Use

Since the ultimate origin of Miqu is at this time unknown beyond speculation, this model is for noncommercial research use only.

<br/>
<br/>


# [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_alchemonaut__QuartetAnemoi-70B-t0.0001)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |76.86|
|AI2 Reasoning Challenge (25-Shot)|73.38|
|HellaSwag (10-Shot)              |88.9|
|MMLU (5-Shot)                    |75.42|
|TruthfulQA (0-shot)              |69.53|
|Winogrande (5-shot)              |85.32|
|GSM8k (5-shot)                   |68.61|