Downloads · 30 days
5
9% of all-time downloads
hermite_sakana-3models-7b-hermite-optimal
lejelly/hermite_sakana-3models-7b-hermite-optimal
hermite_sakana-3models-7b-hermite-optimal is a machine learning model from lejelly. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
54
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Model type
- mistral
- Access
- Public
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026
- SHA
- 0b9ddf4e
Base models
Model card
From the Hugging Face model README
hermite_sakana-3models-7b-hermite-optimal
Hermite 補間で最適化された λ によるモデルマージ。
Merge Configuration
| Parameter | Value |
|---|---|
| Method | Hermite interpolation (Phase 2 optimized) |
| λ | [0.266233, 0.422976, 0.310791] |
| dtype | torch.float16 |
- Model 0 (
augmxnt/shisa-gamma-7b-v1): λ=0.266233 - Model 1 (
WizardLMTeam/WizardMath-7B-V1.1): λ=0.422976 - Model 2 (
GAIR/Abel-7B-002): λ=0.310791
Tokenizer
Union tokenizer (mergekit-style): vocab size = 32032
Formula
θ* = Σ_k λ_k θ_k
The mixing weights λ were optimized by minimizing the Hermite polynomial approximation of the loss function (see Phase 2).
- Type
- mistral
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026