Preview / Testing tune of GLM4-9B for data mix and hyperparameters. I'm hoping to find a roughly optimal SFT setup for GLM 9B base, before testing KTO and transfering over the setup to the new Arcee GLM4-32B-Base pretrain.
This is a hybrid thinking model that defaults to no thinking, but can think if prompted to and prefilled with the <think> tags.
| dataset | version | metric | mode | Marvin-9B_hf-vllm |
|---|---|---|---|---|
| GPQA_diamond | 5aeece | accuracy | gen | 33.33 |
| ARC-c | 1e0de5 | accuracy | gen | 82.71 |
| dataset | version | metric | mode | GLM-4-9B-0414_hf-vllm |
|---|---|---|---|---|
| GPQA_diamond | 5aeece | accuracy | gen | 34.34 |
About equivalent on GPQA to the official checkpoint w/o RL which is pretty nice too.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ConicCat/GL-Marvin-9B-Preview
Base model
zai-org/GLM-4-9B-0414
Finetuned
zai-org/GLM-4.1V-9B-Base
Finetuned
ConicCat/GLM-4.1V-Text-9B-Base