Downloads · 30 days
4
18% of all-time downloads
wdlctc/marin-8b-cpt-plain-lr4e4
marin-8b-cpt-plain-lr4e4 is a machine learning model from wdlctc. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Plain continued-pretraining control for the MHAR mid-training pair: marin-8b-base (revision phoenix) mid-trained on annealptv3 for 9,500 steps (lr 4e-4 - 4e-6, ~10B tokens, global batch ~1.05M tokens), identical sched…
Downloads · 30 days
4
18% of all-time downloads
All-time downloads
22
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
Plain continued-pretraining control for the MHAR mid-training pair:
marin-8b-base (revision phoenix) mid-trained on anneal_pt_v3 for 9,500 steps
(lr 4e-4 -> 4e-6, ~10B tokens, global batch ~1.05M tokens), identical
schedule/data order as wdlctc/marin-8b-cpt-mhar-delta. Final EMA
checkpoint. Standard Llama architecture.
Eval (final EMA): GSM8K 47.0 (strict), GPQA 31.5, MMLU 64.3, HumanEval 40.9, MBPP 38.6, MATH 19.1 (math_verify).