Add real GGUF tensor payload and clarify fictional 217T declaration
Browse files- README.md +3 -2
- config.json +2 -1
- ember-tenant-f16.gguf +0 -0
- model-index.json +2 -2
README.md
CHANGED
|
@@ -16,13 +16,13 @@ num_parameters: 217T
|
|
| 16 |
|
| 17 |
**217 trillion declared parameters.**
|
| 18 |
|
| 19 |
-
> This is a fictional
|
| 20 |
|
| 21 |
## Highlights
|
| 22 |
|
| 23 |
* **217,000,000,000,000 declared parameters** (217T)
|
| 24 |
* **3.517× larger** than The Quettamind (61.718T)
|
| 25 |
-
*
|
| 26 |
* Named for a tenant that occupies every available ember of the parameter budget
|
| 27 |
|
| 28 |
## Comparison
|
|
@@ -49,6 +49,7 @@ num_parameters: 217T
|
|
| 49 |
|
| 50 |
## Files
|
| 51 |
|
|
|
|
| 52 |
* `config.json` — fictional architecture and parameter declaration
|
| 53 |
* `model-index.json` — machine-readable provenance and status
|
| 54 |
* `LICENSE.md` — MIT license retained from the source resource
|
|
|
|
| 16 |
|
| 17 |
**217 trillion declared parameters.**
|
| 18 |
|
| 19 |
+
> This is a fictional model concept inspired by [The Quettamind](https://huggingface.co/yeths/The-Quettamind). It includes a tiny real GGUF tensor payload for format inspection, but is not a trained or useful 217T model. The 217T figure is intentionally declared for the joke/benchmark-card format.
|
| 20 |
|
| 21 |
## Highlights
|
| 22 |
|
| 23 |
* **217,000,000,000,000 declared parameters** (217T)
|
| 24 |
* **3.517× larger** than The Quettamind (61.718T)
|
| 25 |
+
* A valid GGUF container with one real F16 tensor value and a deliberately tiny storage footprint
|
| 26 |
* Named for a tenant that occupies every available ember of the parameter budget
|
| 27 |
|
| 28 |
## Comparison
|
|
|
|
| 49 |
|
| 50 |
## Files
|
| 51 |
|
| 52 |
+
* `ember-tenant-f16.gguf` — valid GGUF container with one real tensor value; not a complete model
|
| 53 |
* `config.json` — fictional architecture and parameter declaration
|
| 54 |
* `model-index.json` — machine-readable provenance and status
|
| 55 |
* `LICENSE.md` — MIT license retained from the source resource
|
config.json
CHANGED
|
@@ -5,7 +5,8 @@
|
|
| 5 |
"model_name": "Ember-Tenant",
|
| 6 |
"declared_parameters": 217000000000000,
|
| 7 |
"declared_parameters_human": "217T",
|
| 8 |
-
"weights_present":
|
|
|
|
| 9 |
"inference_supported": false,
|
| 10 |
"fictional": true,
|
| 11 |
"source_model": "yeths/The-Quettamind"
|
|
|
|
| 5 |
"model_name": "Ember-Tenant",
|
| 6 |
"declared_parameters": 217000000000000,
|
| 7 |
"declared_parameters_human": "217T",
|
| 8 |
+
"weights_present": true,
|
| 9 |
+
"tensor_payload": "one F16 value; incomplete model",
|
| 10 |
"inference_supported": false,
|
| 11 |
"fictional": true,
|
| 12 |
"source_model": "yeths/The-Quettamind"
|
ember-tenant-f16.gguf
CHANGED
|
Binary files a/ember-tenant-f16.gguf and b/ember-tenant-f16.gguf differ
|
|
|
model-index.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"relationship": "presentation and metadata inspiration"
|
| 11 |
},
|
| 12 |
"weights": {
|
| 13 |
-
"included":
|
| 14 |
-
"
|
| 15 |
}
|
| 16 |
}
|
|
|
|
| 10 |
"relationship": "presentation and metadata inspiration"
|
| 11 |
},
|
| 12 |
"weights": {
|
| 13 |
+
"included": true,
|
| 14 |
+
"description": "One real F16 tensor value is included; this is not a trained model."
|
| 15 |
}
|
| 16 |
}
|