You can deploy this model and start earning money today!

lejelly/
deepseek-7b-math-hendrycksmath-lambda03

Name: deepseek-7b-math-hendrycksmath-lambda03
Rating: 2.5 (8 reviews)

Views

No views yet

deepseek-7b-math-hendrycksmath-lambda03

2モデルの線形補間マージモデル。

Parameter	Value
Model A	`deepseek-ai/deepseek-math-7b-instruct`
Model B	`jahyungu/deepseek-math-7b-instruct_hendrycks_math`
λ_a	0.30
λ_b	0.70
Formula	θ* = 0.30 × θ_a + 0.70 × θ_b
dtype	torch.float16

Union tokenizer (mergekit-style): vocabularies of both models are merged.

For tokens missing from a model, the other model's embedding is used as fallback before linear interpolation.

This model was created by linearly interpolating the parameters of two models:

Model A (deepseek-ai/deepseek-math-7b-instruct): weight = 0.30
Model B (jahyungu/deepseek-math-7b-instruct_hendrycks_math): weight = 0.70