Downloads · 30 days
0
aviralku/mr9b-layeraudit-8node-215
mr9b-layeraudit-8node-215 is a machine learning model from aviralku. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
Mid-training research checkpoints from a fully-async GRPO run with the pipelined frozen-E layer audit enabled (metareasoning.layeraudit.enable=true).
Downloads · 30 days
0
Access
Public
Updated Jul 21, 2026
Repo size
75.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors75.3 GB · 100%
From the Hugging Face model README
Mid-training research checkpoints from a fully-async GRPO run with the
pipelined frozen-E layer audit enabled (meta_reasoning.layer_audit.enable=true).
model_type: qwen3_5, 32 layers)mr9b_layeraudit_8node_215_20260718_231300meta_reason_rl_h100_5nodeEach subfolder is a standalone HF model (weights + tokenizer + chat template):
global_step_68/global_step_69/from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("aviralku/mr9b-layeraudit-8node-215", subfolder="global_step_69")
t = AutoTokenizer.from_pretrained("aviralku/mr9b-layeraudit-8node-215", subfolder="global_step_69")
Private research checkpoints; not an official release.