Publish NEO v1 model card and base provenance
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
---
|
| 7 |
+
# NEO
|
| 8 |
+
|
| 9 |
+
NEO = Neural Expert Orchestrator.
|
| 10 |
+
|
| 11 |
+
Release: v1 (September 29, 2026). Model card only; this repository does not yet contain model weights.
|
| 12 |
+
|
| 13 |
+
NEO v1 is the HYPERneocloud serving name for DeepSeek-R1-Distill-Qwen-14B. The currently verified serving configuration uses upstream revision `1df8507178afcc1bef68cd8c393f61a886323761`. It is not presented as newly trained or independently owned base weights. No NEO fine-tuned adapter is verified as loaded in this endpoint.
|
| 14 |
+
|
| 15 |
+
Upstream model and license:
|
| 16 |
+
- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
| 17 |
+
- Exact revision was verified using the model-hub revision API.
|
| 18 |
+
- Upstream card identifies the license as MIT. Preserve the original license and attribution in any redistributed artifact.
|
| 19 |
+
|
| 20 |
+
The September 29 serving check produced a complete greeting through the model's chat template. This single smoke test is not a capability benchmark. Its output included reasoning text before a final-answer separator; customer-facing output separation remains a release gate.
|
| 21 |
+
|
| 22 |
+
Hosted API, price dimensions, customer keys, checkout availability and public repository destination are pending release verification. This draft promises none of them.
|