McaTech commited on
Commit
2dedfb1
·
verified ·
1 Parent(s): dbccb99

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -8
README.md CHANGED
@@ -1,4 +1,4 @@
1
- ````yaml
2
  ---
3
  license: apache-2.0
4
  language:
@@ -16,15 +16,15 @@ inference: true
16
  pipeline_tag: text-generation
17
  ---
18
 
19
- # Model Card for ChatNONET
20
 
21
- **ChatNONET** is a family of **offline**, quantized large language models fine-tuned for **question answering** with **direct, concise answers**. Designed for local execution using `llama.cpp`, ChatNONET is available in multiple sizes and optimized for Android or Python-based environments.
22
 
23
  ## Model Details
24
 
25
  ### Model Description
26
 
27
- ChatNONET is intended for lightweight offline use, particularly on local devices like mobile phones or single-board computers. The models have been **fine-tuned for direct-answer QA** and quantized to **int8 (q8_0)** using `llama.cpp`.
28
 
29
  | Model Name | Base Model | Size |
30
  |----------------------------------|--------------------|--------|
@@ -61,7 +61,7 @@ ChatNONET is intended for lightweight offline use, particularly on local devices
61
 
62
  ## Bias, Risks, and Limitations
63
 
64
- ChatNONET may reproduce biases present in its base models or fine-tuning data. Outputs should not be relied upon for sensitive or critical decisions.
65
 
66
  ### Recommendations
67
 
@@ -111,7 +111,7 @@ make
111
  title={ChatNONET: Offline Quantized Q&A Models},
112
  author={Michael Cobol Agan},
113
  year={2025},
114
- note={\url{https://huggingface.co/your-model-repo}},
115
  }
116
  ```
117
 
@@ -119,5 +119,3 @@ make
119
 
120
  * **Author:** Michael Cobol Agan (McaTech)
121
  * **Website / Download App:** https://mcatech.odoo.com/innovation
122
-
123
- ```
 
1
+
2
  ---
3
  license: apache-2.0
4
  language:
 
16
  pipeline_tag: text-generation
17
  ---
18
 
19
+ # NONET
20
 
21
+ **NONET** is a family of **offline**, quantized large language models fine-tuned for **question answering** with **direct, concise answers**. Designed for local execution using `llama.cpp`, NONET is available in multiple sizes and optimized for Android or Python-based environments.
22
 
23
  ## Model Details
24
 
25
  ### Model Description
26
 
27
+ NONET is intended for lightweight offline use, particularly on local devices like mobile phones or single-board computers. The models have been **fine-tuned for direct-answer QA** and quantized to **int8 (q8_0)** using `llama.cpp`.
28
 
29
  | Model Name | Base Model | Size |
30
  |----------------------------------|--------------------|--------|
 
61
 
62
  ## Bias, Risks, and Limitations
63
 
64
+ NONET may reproduce biases present in its base models or fine-tuning data. Outputs should not be relied upon for sensitive or critical decisions.
65
 
66
  ### Recommendations
67
 
 
111
  title={ChatNONET: Offline Quantized Q&A Models},
112
  author={Michael Cobol Agan},
113
  year={2025},
114
+ note={\url{https://huggingface.co/McaTech/Nonet}},
115
  }
116
  ```
117
 
 
119
 
120
  * **Author:** Michael Cobol Agan (McaTech)
121
  * **Website / Download App:** https://mcatech.odoo.com/innovation