BoreanGale-70B
A merge using a custom algorithm (NearSwap) of:
Quants
Several quants are available thanks to community efforts.
Type | Misc | Author |
---|---|---|
GGUF | iMat Q3 | Nexesenex |
GGUF | iMat | mradermacher |
GGUF | Full Set | mradermacher |
GGUF | Misc | LoneStriker |
exl2 | 2.4 bpw | LoneStriker |
exl2 | 3.5 bpw | LoneStriker |
exl2 | 4.0 bpw | LoneStriker |
exl2 | 4.65 bpw | LoneStriker |
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 (WinterGoddess) value. A parameter t specifies the sameness threshold. When the distance between two values is below t, the weight from the secondary model (WinterGoddess) is used.
This version of the model uses t = 0.001. At this t, about 10% of weights are fully switched to WinterGoddess. Model quality rapidly degrades above t = 0.0025:
- t = 0.0001 (~0.8% full swap): QuartetAnemoi-70B-t0.0001
- t = 0.0003 (~2% full swap)
- t = 0.001 (~10% full swap): This model
- 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
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. | 76.48 |
AI2 Reasoning Challenge (25-Shot) | 73.89 |
HellaSwag (10-Shot) | 89.37 |
MMLU (5-Shot) | 75.19 |
TruthfulQA (0-shot) | 68.6 |
Winogrande (5-shot) | 84.53 |
GSM8k (5-shot) | 67.32 |
- Downloads last month
- 187
Model tree for alchemonaut/BoreanGale-70B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.890
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.370
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard75.190
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard68.600
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard84.530
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard67.320