Downloads · 30 days
6
6% of all-time downloads
nanochat-d24-nested-dense1-fullce-probe-core-20260416
atrost/nanochat-d24-nested-dense1-fullce-probe-core-20260416
nanochat-d24-nested-dense1-fullce-probe-core-20260416 is a machine learning model from atrost. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repo contains the full nested Nanochat checkpoint at the repo root and extracted prefix submodels in subfolders.
All-time downloads
98
Public
Repo size
67 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin33.5 GB · 100%
At a glance
- Model type
- nanochat
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- b67761b7
Model card
From the Hugging Face model README
atrost/nanochat-d24-nested-dense1-fullce-probe-core-20260416
This repo contains the full nested Nanochat checkpoint at the repo root and extracted prefix submodels in subfolders.
Loading with Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "atrost/nanochat-d24-nested-dense1-fullce-probe-core-20260416"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True, torch_dtype="auto")
small = AutoModelForCausalLM.from_pretrained(
repo_id,
subfolder="prefix-1",
trust_remote_code=True,
torch_dtype="auto",
)
Available extracted prefixes: prefix-1, prefix-2, prefix-3, prefix-4, prefix-5, prefix-6, prefix-7, prefix-8, prefix-9, prefix-10, prefix-11.
trust_remote_code=True is required because this model uses a custom nested architecture and tokenizer.
- Type
- nanochat
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026