Any-to-Any
Transformers
Safetensors
multilingual
minicpmo
feature-extraction
minicpm-o
omni
vision
ocr
multi-image
video
custom_code
audio
speech
voice cloning
live Streaming
realtime speech conversation
asr
tts
4-bit precision
gptq
Instructions to use openbmb/MiniCPM-o-2_6-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-o-2_6-int4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-o-2_6-int4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_minicpmo.py
Browse files- modeling_minicpmo.py +2 -2
modeling_minicpmo.py
CHANGED
|
@@ -960,7 +960,7 @@ class MiniCPMO(MiniCPMOPreTrainedModel):
|
|
| 960 |
"top_k": 100,
|
| 961 |
"temperature": 0.7,
|
| 962 |
"do_sample": True,
|
| 963 |
-
"repetition_penalty": 1.
|
| 964 |
}
|
| 965 |
else:
|
| 966 |
generation_config = {
|
|
@@ -1163,7 +1163,7 @@ class MiniCPMO(MiniCPMOPreTrainedModel):
|
|
| 1163 |
"top_k": 100,
|
| 1164 |
"temperature": 0.7,
|
| 1165 |
"do_sample": True,
|
| 1166 |
-
"repetition_penalty": 1.
|
| 1167 |
}
|
| 1168 |
else:
|
| 1169 |
generation_config = {
|
|
|
|
| 960 |
"top_k": 100,
|
| 961 |
"temperature": 0.7,
|
| 962 |
"do_sample": True,
|
| 963 |
+
"repetition_penalty": 1.05,
|
| 964 |
}
|
| 965 |
else:
|
| 966 |
generation_config = {
|
|
|
|
| 1163 |
"top_k": 100,
|
| 1164 |
"temperature": 0.7,
|
| 1165 |
"do_sample": True,
|
| 1166 |
+
"repetition_penalty": 1.05,
|
| 1167 |
}
|
| 1168 |
else:
|
| 1169 |
generation_config = {
|