tyraepaul commited on
Commit
ce08ea1
·
verified ·
1 Parent(s): 06454d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -16,6 +16,7 @@ pipeline_tag: text-generation
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.
@@ -59,6 +60,7 @@ python3 stokfile.py -m stok-0.3.json -speed
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 |
 
16
  | stok-0.4-mini | 485k | 135MB |
17
  | stok-0.4 | 3.2m | 887MB |
18
  | stok-0.4-large | 17.33m | 4.7GB |
19
+ | stok-0.4.1 | 3.31m | 919MB |
20
  ## Description
21
  stok is a family of models designed to run better at smaller parameter counts and maintain speed despite model size.
22
  stok-sub-1 will contain all versions of the stok model, prior to releasing stok-1.
 
60
  | stok-0.4-mini | 10/15 | 32,515 t/s |
61
  | stok-0.4 | 11/15 | 34,308 t/s |
62
  | stok-0.4-large | 11/15 | 31,775 t/s |
63
+ | stok-0.4.1 | 11/15 | 32,263 t/s |
64
  | TinyLLama-v0 (F32) | 0/15 | 1,695 t/s |
65
  | Gemma-3-270m-it (F16) | 12/15 | 46 t/s |
66
  | H2o danube3 500m chat(F32)| 8/15 | 21 t/s |