MastLLM commited on
Commit
b179934
·
verified ·
1 Parent(s): 602b6ba

Rebrand: openTARS models are now made by MastLLM

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ language:
15
 
16
  # Murph
17
 
18
- Murph is the small request classifier built into [openTARS](https://project-opentars.github.io/OpenTARS/). For each request it decides the **kind of task**, so the app can pick the right model and tools before any language model runs.
19
 
20
  It is not a language model. It is a softmax logistic regression over word pieces (2 to 5 letters), words and word pairs, with TF-IDF weights. It runs in plain Python on the CPU in about 0.2 ms per request, uses no GPU, and the whole model is one JSON file of about 4 MB.
21
 
@@ -50,7 +50,7 @@ The model also stores a confidence threshold and a coverage minimum, so the app
50
 
51
  ## Training and results
52
 
53
- - Trained on 3,034 request phrases in five languages: examples from the openTARS project plus phrases written by a larger model. Phrases similar to the evaluation phrases were removed from training.
54
  - Cross-validation accuracy stored in the file: 88.9%.
55
  - openTARS evaluation sets, measured on 18 October 2026: 170 of 175 across languages and 85 of 86 on the check set. The evaluation phrases were seen during development, so treat these as a sanity check, not as a benchmark.
56
 
 
15
 
16
  # Murph
17
 
18
+ Murph is the small request classifier built into [openTARS](https://mastllm.github.io/OpenTARS/). For each request it decides the **kind of task**, so the app can pick the right model and tools before any language model runs.
19
 
20
  It is not a language model. It is a softmax logistic regression over word pieces (2 to 5 letters), words and word pairs, with TF-IDF weights. It runs in plain Python on the CPU in about 0.2 ms per request, uses no GPU, and the whole model is one JSON file of about 4 MB.
21
 
 
50
 
51
  ## Training and results
52
 
53
+ - Trained on 3,034 request phrases in five languages: examples from MastLLM plus phrases written by a larger model. Phrases similar to the evaluation phrases were removed from training.
54
  - Cross-validation accuracy stored in the file: 88.9%.
55
  - openTARS evaluation sets, measured on 18 October 2026: 170 of 175 across languages and 85 of 86 on the check set. The evaluation phrases were seen during development, so treat these as a sanity check, not as a benchmark.
56