Hugging Face's logo

Maincode
/
Matilda-Jev-v1

Zero-Shot Classification
Transformers
Safetensors
English
matilda_jev
feature-extraction
decision-model
typed-decisions
jev
maincode
custom_code
Model card Files
xet
 Community
1
arsh-maincode commited on
Commit
1f25c5a
·
verified ·
1 Parent(s): 2bae151

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- pretty_name: MATILDA-jev by Maincode
3
  license: apache-2.0
4
  language:
5
  - en
@@ -14,9 +14,9 @@ base_model:
14
  - Qwen/Qwen3.8-27B
15
  ---
16
 
17
- # MATILDA-jev by Maincode
18
 
19
- MATILDA-jev is Maincode's one-pass decision model. It scores the options supplied in a `choice`, `noul` (yes/no), or ordered `score` question. It accepts text or JSON state and optional images. This is a decision checkpoint with a 255-option readout, not a text-generation checkpoint.
20
 
21
  This configuration edition uses `MatildaJevModel`, `MatildaJevConfig`, and MATILDA tokenizer/processor classes. **Use the bundled runtime below, or load the custom AutoClasses with `trust_remote_code=True`.** The package includes the backbone weights, decision readout, tokenizer, preprocessing configuration and calibrated temperature.
22
 
@@ -37,7 +37,7 @@ Evaluated with Decision Index 0.2.1 over 150,317 requests (currently awaiting of
37
 
38
  | Model | Parameters | Decision Index | Raw | Breadth |
39
  |---|---:|---:|---:|---:|
40
- | MATILDA-jev | 26.1B | 59.59 | 69.18 | 58.39 |
41
 
42
  | Knowledge & Reasoning | Language | Retrieval & Classification | Tools & Automation | Arts & Human Taste |
43
  |---:|---:|---:|---:|---:|
@@ -51,7 +51,6 @@ Use Python 3.12. Install PyTorch 2.14.0 and torchvision 0.29.0 for your accelera
51
 
52
  ```bash
53
  python -m pip install huggingface_hub
54
- # Authenticate with an account that has access while the repository is private.
55
  hf auth login
56
  hf download Maincode/matilda-jev-v1 --local-dir ./matilda-jev-v1
57
  python -m pip install -r ./matilda-jev-v1/requirements-runtime.txt
 
1
  ---
2
+ pretty_name: Matilda-Jev by Maincode
3
  license: apache-2.0
4
  language:
5
  - en
 
14
  - Qwen/Qwen3.8-27B
15
  ---
16
 
17
+ # Matilda-Jev by Maincode
18
 
19
+ Matilda-Jev is Maincode's one-pass decision model. It scores the options supplied in a `choice`, `noul` (yes/no), or ordered `score` question. It accepts text or JSON state and optional images. This is a decision checkpoint with a 255-option readout, not a text-generation checkpoint.
20
 
21
  This configuration edition uses `MatildaJevModel`, `MatildaJevConfig`, and MATILDA tokenizer/processor classes. **Use the bundled runtime below, or load the custom AutoClasses with `trust_remote_code=True`.** The package includes the backbone weights, decision readout, tokenizer, preprocessing configuration and calibrated temperature.
22
 
 
37
 
38
  | Model | Parameters | Decision Index | Raw | Breadth |
39
  |---|---:|---:|---:|---:|
40
+ | Matilda-Jev | 26.1B | 59.59 | 69.18 | 58.39 |
41
 
42
  | Knowledge & Reasoning | Language | Retrieval & Classification | Tools & Automation | Arts & Human Taste |
43
  |---:|---:|---:|---:|---:|
 
51
 
52
  ```bash
53
  python -m pip install huggingface_hub
 
54
  hf auth login
55
  hf download Maincode/matilda-jev-v1 --local-dir ./matilda-jev-v1
56
  python -m pip install -r ./matilda-jev-v1/requirements-runtime.txt