Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,18 @@ It was produced by distilling of Qwen3 235B logits onto Mistral Nemo after token
|
|
| 16 |
|
| 17 |
Like Qwen3, it features both thinking and non-thinking modes. As suggested by the name, it is a weird little guy produced through alchemy.
|
| 18 |
|
| 19 |
-
Homunculus is a surprisingly powerful model for its size, showing strong performance in real-world applications despite being able to fit on consumer GPUs.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
Like Qwen3, it features both thinking and non-thinking modes. As suggested by the name, it is a weird little guy produced through alchemy.
|
| 18 |
|
| 19 |
+
Homunculus is a surprisingly powerful model for its size, showing strong performance in real-world applications despite being able to fit on consumer GPUs.
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Basic use
|
| 23 |
+
|
| 24 |
+
```
|
| 25 |
+
# Use a pipeline as a high-level helper
|
| 26 |
+
from transformers import pipeline
|
| 27 |
+
|
| 28 |
+
pipe = pipeline("text-generation", model="arcee-ai/Homunculus")
|
| 29 |
+
messages = [
|
| 30 |
+
{"role": "user", "content": "Who are you?"},
|
| 31 |
+
]
|
| 32 |
+
pipe(messages)
|
| 33 |
+
```
|