-
**Describe the bug**
With the new Onnx package that allows us to use the SLMs like Phi-3 by just loading a model from file, I think there's an issue when I try to use the [local embeddings](https://g…
-
**Describe the bug**
When using a dataframe with newer/nullable dtypes, such as the following, I am unable to generate any reports
```python
In[83]: df4.dtypes
Out[83]:
str_col string
…
mands updated
2 years ago
-
Alright, so I spent several hours thinking it was a dependency issue, only to discover that it was actually a change in the model itself that was uploaded to Huggingface. :/
To confirm, I just chan…
-
This structure will help us in keeping all the different distributions separate and th…
-
### Your current environment
from langchain_community.llms import VLLMOpenAI
from PIL import Image
llm = VLLMOpenAI(
openai_api_key="EMPTY",
openai_api_base="http://150.0.2.236:8888/v…
-
### Describe the documentation issue
All of the samples appear to be in Python. Nothing in C, or C#.
Python is awesome for academia, but most Windows desktop App developers are developing desktop…
-
Hi, I've been exploring this repo for the past couple of days and I find your work here really amazing. I'm curious if there are any plans to add support for the Phi-3-vision-128k-instruct model to th…
-
microsoft/phi-1_5 这种高质量小模型的微调非常有意义。
-
Getting this message:
File "/anaconda3/lib/python3.11/site-packages/transformers/processing_utils.py", line 926, in apply_chat_template
raise ValueError(
ValueError: No chat template is set f…
-
**Describe the bug**
Deploy a multimodal model, such as Phi-3.5-vision-instruct. Use the default value for `--limit-mm-per-prompt`.
When more than one image is input, nothing will be returne…