Downloads · 30 days
26
13% of all-time downloads
NedoLM-0.8B-SFT-6478-GGUF
Ethosoft/NedoLM-0.8B-SFT-6478-GGUF
NedoLM-0.8B-SFT-6478-GGUF is a machine learning model from Ethosoft. 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 llama.cpp.
Final step00006478.pt export for the custom NedoLM llama.cpp backend.
All-time downloads
205
Public
Repo size
1.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.6 GB · 100%
At a glance
- Library
- llama.cpp
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026
- SHA
- 4c8e4214
Model card
From the Hugging Face model README
NedoLM 0.8B SFT — step 6478 GGUF
Final step_00006478.pt export for the custom NedoLM llama.cpp backend.
- Architecture: NedoLM
- Parameters: ~0.8B
- Context: 4096
- Sliding window: 2048
- Tokenizer: exact NDSRF004
- NDSRF004 vocab SHA256:
72412d981dac65a29d1767bc98821fc2bcffc2de53c534e7c719598515bfb600 - GGUF SHA256:
780eb3a95468b599cbaf896c894b3a9c28802d35f5271640c1906e7e9f769eed - Rust production tokenizer ↔ patched llama.cpp ID parity: PASS
- Patched llama.cpp inference smoke: PASS
This model requires the NedoLM-patched llama.cpp runtime. Stock llama.cpp builds do not yet implement the NedoLM architecture.
- Library
- llama.cpp
- Languages
- tr
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026