Downloads · 30 days
6
21% of all-time downloads
verl-edits-counterfact_cot_correctness_only-step25
ztiganj/verl-edits-counterfact_cot_correctness_only-step25
verl-edits-counterfact_cot_correctness_only-step25 is a machine learning model from ztiganj. 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 llama3.1.
Compact Hugging Face inference export from a VERL FSDP actor checkpoint.
All-time downloads
29
Public
Parameters
8B
32.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- License
- llama3.1
- Model type
- llama
- Access
- Public
- Created
- Jun 4, 2026
- Updated
- Jun 4, 2026
- SHA
- 518a386c
Model card
From the Hugging Face model README
ztiganj/verl-edits-counterfact_cot_correctness_only-step25
Compact Hugging Face inference export from a VERL FSDP actor checkpoint.
Source
- Modal volume:
verl-setup-outputs - Source actor directory:
/checkpoints/verl_edits/counterfact_cot_correctness_only/global_step_25/actor - Run:
counterfact_cot_correctness_only - Global step:
25
Conversion
Converted with the official VERL FSDP model merger:
python -m verl.model_merger merge --backend fsdp --local_dir <actor_dir> --target_dir <target_dir>
The original training step stored FSDP actor shards plus extra state. This repository keeps only the merged Hugging Face inference checkpoint, tokenizer/config files, and a migration manifest.
Migration Status
This repository was made public after verifying the compact export and checking that projected public Hugging Face storage remained below the configured guardrail.
- Type
- llama
- License
- llama3.1
- Created
- Jun 4, 2026
- Updated
- Jun 4, 2026