Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,7 @@ pipeline_tag: text-generation
|
|
| 15 |
| stok-0.3.1 | 982k | 138MB |
|
| 16 |
| stok-0.4-mini | 485k | 135MB |
|
| 17 |
| stok-0.4 | 3.2m | 887MB |
|
|
|
|
| 18 |
## Description
|
| 19 |
stok is a family of models designed to run better at smaller parameter counts and maintain speed despite model size.
|
| 20 |
stok-sub-1 will contain all versions of the stok model, prior to releasing stok-1.
|
|
@@ -55,8 +56,9 @@ python3 stokfile.py -m stok-0.3.json -speed
|
|
| 55 |
| stok-0.3-large | 8/15 | 149,526 t/s |
|
| 56 |
| stok-0.3-125m | 8/15 | 122,625 t/s |
|
| 57 |
| stok-0.3.1 | 8/15 | 34,521 t/s |
|
| 58 |
-
| stok-0.4-mini |
|
| 59 |
-
| stok-0.4 |
|
|
|
|
| 60 |
| TinyLLama-v0 (F32) | 0/15 | 1,695 t/s |
|
| 61 |
| Gemma-3-270m-it (F16) | 12/15 | 46 t/s |
|
| 62 |
| H2o danube3 500m chat(F32)| 8/15 | 21 t/s |
|
|
|
|
| 15 |
| stok-0.3.1 | 982k | 138MB |
|
| 16 |
| stok-0.4-mini | 485k | 135MB |
|
| 17 |
| stok-0.4 | 3.2m | 887MB |
|
| 18 |
+
| stok-0.4-large | 17.33m | 4.7GB |
|
| 19 |
## Description
|
| 20 |
stok is a family of models designed to run better at smaller parameter counts and maintain speed despite model size.
|
| 21 |
stok-sub-1 will contain all versions of the stok model, prior to releasing stok-1.
|
|
|
|
| 56 |
| stok-0.3-large | 8/15 | 149,526 t/s |
|
| 57 |
| stok-0.3-125m | 8/15 | 122,625 t/s |
|
| 58 |
| stok-0.3.1 | 8/15 | 34,521 t/s |
|
| 59 |
+
| stok-0.4-mini | 10/15 | 32,515 t/s |
|
| 60 |
+
| stok-0.4 | 11/15 | 34,308 t/s |
|
| 61 |
+
| stok-0.4-large | 11/15 | 31,775 t/s |
|
| 62 |
| TinyLLama-v0 (F32) | 0/15 | 1,695 t/s |
|
| 63 |
| Gemma-3-270m-it (F16) | 12/15 | 46 t/s |
|
| 64 |
| H2o danube3 500m chat(F32)| 8/15 | 21 t/s |
|