Update README.md
Browse files
README.md
CHANGED
|
@@ -7,12 +7,36 @@ license: other
|
|
| 7 |
license_name: modified-mit
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
-
<div
|
| 11 |
-
<
|
| 12 |
-
|
| 13 |
-
</
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
</div>
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
<div align="center" style="line-height:1">
|
| 18 |
<a href="https://www.kimi.com" target="_blank"><img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-Kimi%20K2-ff6b6b?color=1783ff&logoColor=white"/></a>
|
|
|
|
| 7 |
license_name: modified-mit
|
| 8 |
library_name: transformers
|
| 9 |
---
|
| 10 |
+
<div>
|
| 11 |
+
<p style="margin-bottom: 0; margin-top: 0;">
|
| 12 |
+
<strong>Learn how to run Kimi-K2 Dynamic GGUFs - <a href="https://docs.unsloth.ai/basics/kimi-k2">Read our Guide!</a></strong>
|
| 13 |
+
</p>
|
| 14 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 15 |
+
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
| 16 |
+
</p>
|
| 17 |
+
<div style="margin-top: 0;display: flex; gap: 5px; align-items: center; ">
|
| 18 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 19 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 20 |
+
</a>
|
| 21 |
+
<a href="https://discord.gg/unsloth">
|
| 22 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 23 |
+
</a>
|
| 24 |
+
<a href="https://docs.unsloth.ai/basics/deepseek-r1-0528-how-to-run-locally">
|
| 25 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 26 |
+
</a>
|
| 27 |
+
</div>
|
| 28 |
+
<h1 style="margin-top: 0rem;">🌙 Kimi K2 Usage Guidelines</h1>
|
| 29 |
</div>
|
| 30 |
+
|
| 31 |
+
- You can now use the latest update of [llama.cpp](https://github.com/ggml-org/llama.cpp) to run the model.
|
| 32 |
+
- For complete detailed instructions, see our guide: [docs.unsloth.ai/basics/kimi-k2](https://docs.unsloth.ai/basics/kimi-k2)
|
| 33 |
+
|
| 34 |
+
It is recommended to have at least 128GB unified RAM memory to run the small quants. With 16GB VRAM and 256 RAM, expect 5+ tokens/sec.
|
| 35 |
+
For best results, use any 2-bit XL quant or above.
|
| 36 |
+
|
| 37 |
+
Set the temperature to 0.6 recommended) to reduce repetition and incoherence.
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
|
| 41 |
<div align="center" style="line-height:1">
|
| 42 |
<a href="https://www.kimi.com" target="_blank"><img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-Kimi%20K2-ff6b6b?color=1783ff&logoColor=white"/></a>
|