adriandj3 commited on
Commit
b1415dd
路
verified 路
1 Parent(s): 5c251fb

Results section first

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -55,6 +55,13 @@ By **Adrian Ciprian Iancu** 路 [GitHub](https://github.com/ArtyomITA) 路 [Huggin
55
  > [prism-ml/Ternary-Bonsai-2-9B-gguf](https://huggingface.co/prism-ml/Ternary-Bonsai-2-9B-gguf), loaded at scale 0 and
56
  > switched on per request, so normal chat stays exactly the base model.
57
 
 
 
 
 
 
 
 
58
  ## Pick a file
59
 
60
  | file | for | size | what it is |
@@ -63,13 +70,6 @@ By **Adrian Ciprian Iancu** 路 [GitHub](https://github.com/ArtyomITA) 路 [Huggin
63
  | `eval/` | checking my numbers | small | summaries and every answer of the base model and v2 on each benchmark |
64
  | `training/` | rebuilding it | small | data builder, trainer (Blackwell dense mode), benchmark runner |
65
 
66
- ## At a glance
67
-
68
- Every case is asked to the base model (adapter at scale 0) and to v2 on the same llama.cpp server. Greedy decoding,
69
- images at 1024 tokens, `Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf` with the Q8_0 vision projector.
70
-
71
- **Benchmarks are running now** (full ScreenSpot-v2, full ScreenSpot-Pro, GUI-360 test grounding and actions, base model against v2 on the same server). This section is filled in as soon as they finish.
72
-
73
  ## Results
74
 
75
  **Benchmarks are running now** (full ScreenSpot-v2, full ScreenSpot-Pro, GUI-360 test grounding and actions, base model against v2 on the same server). This section is filled in as soon as they finish.
 
55
  > [prism-ml/Ternary-Bonsai-2-9B-gguf](https://huggingface.co/prism-ml/Ternary-Bonsai-2-9B-gguf), loaded at scale 0 and
56
  > switched on per request, so normal chat stays exactly the base model.
57
 
58
+ ## Results at a glance
59
+
60
+ Every case is asked to the base model (adapter at scale 0) and to v2 on the same llama.cpp server. Greedy decoding,
61
+ images at 1024 tokens, `Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf` with the Q8_0 vision projector.
62
+
63
+ **Benchmarks are running now** (full ScreenSpot-v2, full ScreenSpot-Pro, GUI-360 test grounding and actions, base model against v2 on the same server). This section is filled in as soon as they finish.
64
+
65
  ## Pick a file
66
 
67
  | file | for | size | what it is |
 
70
  | `eval/` | checking my numbers | small | summaries and every answer of the base model and v2 on each benchmark |
71
  | `training/` | rebuilding it | small | data builder, trainer (Blackwell dense mode), benchmark runner |
72
 
 
 
 
 
 
 
 
73
  ## Results
74
 
75
  **Benchmarks are running now** (full ScreenSpot-v2, full ScreenSpot-Pro, GUI-360 test grounding and actions, base model against v2 on the same server). This section is filled in as soon as they finish.