Downloads · 30 days
3
16% of all-time downloads
llama-9b-base-v1
Ouroboros-Research/llama-9b-base-v1
llama-9b-base-v1 is a machine learning model from Ouroboros-Research. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Custom hybrid architecture (spec v2.1): NOT loadable by stock transformers. Load with train.src.tools.baseckpt.loadbasecheckpoint from the training harness (see repo AGENTS.md). Weights are bf16 (bitwise-identical to…
All-time downloads
19
Public
Parameters
8.3B
70.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt52 GB · 73%
At a glance
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 3, 2026
- SHA
- 958c1ce4
Model card
From the Hugging Face model README
Llama-9B base (untrained, step 0)
Custom hybrid architecture (spec v2.1): NOT loadable by stock
transformers. Load with train.src.tools.base_ckpt.load_base_checkpoint
from the training harness (see repo AGENTS.md). Weights are bf16
(bitwise-identical to the bf16 donor for donor-sourced params).
init=warm, donor=OriginalModel
- Created
- Sep 2, 2026
- Updated
- Sep 3, 2026