kobkrit commited on
Commit
57d4a5c
·
verified ·
1 Parent(s): 98703d8

Brand line: "Developed by iApp, launched with AIEAT. Part of OpenThai (formerly OpenThaiGPT)."

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -10,6 +10,8 @@ tags: [system-one, decision-model, thai, qwen3.5, quantized, mlx, apple-silicon]
10
 
11
  # OpenThai-SystemOne — mlx-8bit
12
 
 
 
13
  [OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne) is an open Thai + English **System One decision model**: one forward
14
  pass answers typed questions (`choice` over up to 255 options, ordinal `score`, yes/no `noul`) about a text / JSON state with
15
  calibrated probabilities, no text generation. It is a Qwen3.5-0.8B text tower (Thai continued pre-training) plus a 256-slot
@@ -80,4 +82,4 @@ Macro: public 74.2 (original 74.3), Thai 80.0 (original 80.1).
80
  - Scores are single-option-order accuracy on the first 800 records of each set (`scripts/06_eval.py --limit 800`), the same
81
  records for the original and the quantization. `score` subsets report exact level accuracy.
82
  - Base model, data, training and the full benchmark tables: [iapp/OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne).
83
- - License Apache-2.0 (same as the base). Built by iApp Technology / OpenThaiGPT.
 
10
 
11
  # OpenThai-SystemOne — mlx-8bit
12
 
13
+ Developed by iApp, launched with AIEAT. Part of OpenThai (formerly OpenThaiGPT).
14
+
15
  [OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne) is an open Thai + English **System One decision model**: one forward
16
  pass answers typed questions (`choice` over up to 255 options, ordinal `score`, yes/no `noul`) about a text / JSON state with
17
  calibrated probabilities, no text generation. It is a Qwen3.5-0.8B text tower (Thai continued pre-training) plus a 256-slot
 
82
  - Scores are single-option-order accuracy on the first 800 records of each set (`scripts/06_eval.py --limit 800`), the same
83
  records for the original and the quantization. `score` subsets report exact level accuracy.
84
  - Base model, data, training and the full benchmark tables: [iapp/OpenThai-SystemOne](https://huggingface.co/iapp/OpenThai-SystemOne).
85
+ - License Apache-2.0 (same as the base). Developed by iApp, launched with AIEAT.