Gravel 4B

Continued-pretraining of qingy2024/Qwen2.5-4B on 143M tokens from HuggingFaceTB/finemath 4-plus

Downloads last month
8
Safetensors
Model size
3.86B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for qingy2024/Gravel-3.8B-Base

Base model

Qwen/Qwen2.5-3B
Finetuned
(2)
this model

Dataset used to train qingy2024/Gravel-3.8B-Base