QuartetAnemoi-70B-t0.0001
A sequential merge using a custom algorithm (NearSwap) of:
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.
This repo has the GGUF quants. Full weights are available at: alchemonaut/QuartetAnemoi-70B-t0.0001
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
- 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)
License and Use
Since the ultimate origin of Miqu is at this time unknown beyond speculation, this model is for noncommercial research use only.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| 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 |
- Downloads last month
- 83
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.380
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.900
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard75.420
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard69.530
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard85.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard68.610