Update README.md
Browse files
README.md
CHANGED
|
@@ -191,6 +191,14 @@ Designed for Banking and Fintech Institutions
|
|
| 191 |
- FIM (Fill-in-the-Middle) support for code generation
|
| 192 |
- Rich set of domain routing tokens (`__CODING__`, `__PYTHON__`, `__ROBOTICS__`, `__SCIENCE__`, etc.)
|
| 193 |
- Extended robotics and control tokens
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
|
| 195 |
|
| 196 |
|
|
|
|
| 191 |
- FIM (Fill-in-the-Middle) support for code generation
|
| 192 |
- Rich set of domain routing tokens (`__CODING__`, `__PYTHON__`, `__ROBOTICS__`, `__SCIENCE__`, etc.)
|
| 193 |
- Extended robotics and control tokens
|
| 194 |
+
|
| 195 |
+
|
| 196 |
+
### CMS Manhattan Service & Support
|
| 197 |
+
|
| 198 |
+
- Jirack patent guards your technology for competitors
|
| 199 |
+
- Redesign Llama , Qwen , Gemma to Ternary model
|
| 200 |
+
- Re-tain and replace embeddings for Llama , Qwen , Gemma to extend langeages to 347
|
| 201 |
+
- Accelerate inference via high compression 256K tokenizer and replace multiplication with sum operations via Ternary weights
|
| 202 |
|
| 203 |
|
| 204 |
|