-
Model: https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
```console
$ mkdir -p /models/phi-3-vision && cd /models/phi-3-vision
$ git clone https://huggingface.co/microsoft/Phi-3-vision-…
-
Failed to load model: No LM Runtime found for format 'safetensors!
Model: Phi-3.5-vision-instruct-gguf
![image](https://github.com/user-attachments/assets/0f9b1a82-c260-45bb-a286-9118dcefb33c)
…
-
Lots of people have asked to have a local version working that is not reliant on OpenAI.
So far OSS models have seemed to not be good enough but [Phi-3](https://huggingface.co/microsoft/Phi-3-visio…
-
### System Info
- `n1-standard-16` from GCP with 4x NVIDIA T4s
- nvidia-smi: `NVIDIA-SMI 550.54.15`, `Driver Version: 550.54.15`, `CUDA Version: 12.4`
- Using a `NVIDIA GPU Optimized` base image
#…
-
-
**The bug**
The 'quick spot check to verify we can rebuild complex multi-token unicode symbols' check in the `TransformersTokenizer` constructor is failing for Phi-3-vision-128k-instruct.
This i…
-
### Motivation
The latest release of microsoft phi3 4.2b 128k context vision model looks promising in performance and resource saving one too as it boast just 4.2b parameter. So it would be a great f…
-
while running inference after **merging lora weights** with the following script
`
!python -m src.serve.cli \
--model-path /kaggle/working/Phi3-Vision-Finetune/output \
--image-file /kaggle/work…
-
### 🐛 Describe the bug
Repro:
```python
import requests
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor
from ml_dtypes import bfloat16
import …
-
### The model to consider.
from typing import List
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from PIL import Image
from vllm import LLM, SamplingParams
import os
…