Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ library_name: transformers
|
|
| 39 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
| 40 |
The source code can also be used directly.
|
| 41 |
|
| 42 |
-
This model contains Brainstorm 20x, combined with Microsoft's 7B Coder:
|
| 43 |
|
| 44 |
https://huggingface.co/microsoft/NextCoder-7B
|
| 45 |
|
|
@@ -52,6 +52,19 @@ This model requires:
|
|
| 52 |
- Jinja (embedded) or CHATML template
|
| 53 |
- Max context of 32k as per Microsoft specs.
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
---
|
| 56 |
|
| 57 |
# NextCoder-7B
|
|
|
|
| 39 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
| 40 |
The source code can also be used directly.
|
| 41 |
|
| 42 |
+
This model contains Brainstorm 20x, combined with Microsoft's 7B Coder (instruct model):
|
| 43 |
|
| 44 |
https://huggingface.co/microsoft/NextCoder-7B
|
| 45 |
|
|
|
|
| 52 |
- Jinja (embedded) or CHATML template
|
| 53 |
- Max context of 32k as per Microsoft specs.
|
| 54 |
|
| 55 |
+
Settings used for testing (suggested):
|
| 56 |
+
- Temp .3 to .7
|
| 57 |
+
- Rep pen 1.05 to 1.1
|
| 58 |
+
- Topp .8 , minp .05
|
| 59 |
+
- Topk 20
|
| 60 |
+
- No system prompt.
|
| 61 |
+
|
| 62 |
+
This model will respond well to both detailed instructions and step by step refinement and additions to code.
|
| 63 |
+
|
| 64 |
+
As this is an instruct model, it will also benefit from a detailed system prompt too.
|
| 65 |
+
|
| 66 |
+
For simpler coding problems, lower quants will work well; but for complex/multi-step problem solving suggest Q6 or Q8.
|
| 67 |
+
|
| 68 |
---
|
| 69 |
|
| 70 |
# NextCoder-7B
|