Update README.md
Browse files
README.md
CHANGED
|
@@ -46,10 +46,12 @@ https://huggingface.co/microsoft/NextCoder-7B
|
|
| 46 |
|
| 47 |
Information on the models below, and then a complete help section for running LLM / AI models.
|
| 48 |
|
| 49 |
-
The FUSING process enhances model performance and
|
| 50 |
|
| 51 |
Ask the model for code, and you get code asap.
|
| 52 |
|
|
|
|
|
|
|
| 53 |
This model requires:
|
| 54 |
- Jinja (embedded) or CHATML template
|
| 55 |
- Max context of 32k expanded as per Qwen2.5 methods.
|
|
|
|
| 46 |
|
| 47 |
Information on the models below, and then a complete help section for running LLM / AI models.
|
| 48 |
|
| 49 |
+
The FUSING process enhances model performance and the model has minimal to no "reasoning" blocks.
|
| 50 |
|
| 51 |
Ask the model for code, and you get code asap.
|
| 52 |
|
| 53 |
+
Source is in float32 precision to preserve Microsoft Next Coder's 32 bit source.
|
| 54 |
+
|
| 55 |
This model requires:
|
| 56 |
- Jinja (embedded) or CHATML template
|
| 57 |
- Max context of 32k expanded as per Qwen2.5 methods.
|