Update README.md
Browse files
README.md
CHANGED
|
@@ -65,6 +65,34 @@ For simpler coding problems, lower quants will work well; but for complex/multi-
|
|
| 65 |
|
| 66 |
---
|
| 67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
# NextCoder-32B
|
| 69 |
<p align="center">
|
| 70 |
<a href="https://github.com/microsoft/NextCoder">GitHub</a>   |    <a href="https://www.microsoft.com/en-us/research/publication/nextcoder-robust-adaptation-of-code-lms-to-diverse-code-edits/">Paper</a>
|
|
|
|
| 65 |
|
| 66 |
---
|
| 67 |
|
| 68 |
+
<B>QUANTS:</b>
|
| 69 |
+
|
| 70 |
+
---
|
| 71 |
+
|
| 72 |
+
Special Thanks to Team Mradermacher and Team Nightmedia for the quants:
|
| 73 |
+
|
| 74 |
+
GGUF:
|
| 75 |
+
|
| 76 |
+
https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-GGUF
|
| 77 |
+
|
| 78 |
+
GGUF-IMATRIX:
|
| 79 |
+
|
| 80 |
+
https://huggingface.co/mradermacher/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-i1-GGUF
|
| 81 |
+
|
| 82 |
+
MLX:
|
| 83 |
+
|
| 84 |
+
https://huggingface.co/nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-q4-mlx
|
| 85 |
+
|
| 86 |
+
https://huggingface.co/nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-q6-mlx
|
| 87 |
+
|
| 88 |
+
https://huggingface.co/nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-128k-q6-mlx
|
| 89 |
+
|
| 90 |
+
https://huggingface.co/nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-64k-q6-mlx
|
| 91 |
+
|
| 92 |
+
https://huggingface.co/nightmedia/Qwen2.5-Microsoft-NextCoder-Brainstorm20x-42B-64k-q8-mlx
|
| 93 |
+
|
| 94 |
+
---
|
| 95 |
+
|
| 96 |
# NextCoder-32B
|
| 97 |
<p align="center">
|
| 98 |
<a href="https://github.com/microsoft/NextCoder">GitHub</a>   |    <a href="https://www.microsoft.com/en-us/research/publication/nextcoder-robust-adaptation-of-code-lms-to-diverse-code-edits/">Paper</a>
|