-
Hi Team,
I trained Phi3-Vision on my short video captioning dataset.
The training went very well (after multiple attempts), and the model reached a good performance point (i.e.: low train and val…
hm-ca updated
3 months ago
-
I tried running full fine-tuning (`bash scripts/finetune.sh`) with this dataset: https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K
(The first row from the dataset exactly matches [the …
-
**Describe the bug**
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图)
```
swift infer --model_type internvl2-8b-awq --infer_backend lmdeploy
```
```
WARNING:ro…
-
Hello after training Qlora I got produce checkpoint under
```
ll output/lora_vision_test/
adapter_config.json
adapter_model.safetensors
checkpoint-178/
config.json
non_lora_state_dict.bin
…
-
> Please provide us with the following information:
> ---------------------------------------------------------------
### This issue is for a: (mark with an `x`)
```
- [ ] bug report -> please…
-
### Describe the issue
### Context
I encountered an error while attempting to convert a Microsoft Phi3 model to ONNX format using Python and the Transformers library. The conversion process fails wi…
-
**Describe the bug**
The official VLLM Wiki claims support for Phi-3-Vision (microsoft/Phi-3-vision-128k-instruct, Phi3VForCausalLM), but when I try to run it I get the following error:
`[rank0]: Tr…
-
### Describe the documentation issue
I am trying to follow the instructions https://onnxruntime.ai/docs/genai/tutorials/phi3-v.html. I am trying Run with NVIDIA CUDA
approach.
I am able to setup …
-
Hi Team,
When I set **num_crops=0 I get the error: "ValueError: height and width must be > 0"**. Full error is below....
my images are square and small (less than 336x336) already and I don't want…
hm-ca updated
4 months ago
-
### Your current environment
llm = VLLMOpenAI(
openai_api_key="EMPTY",
openai_api_base=api_base,
model_name="microsoft/Phi-3-vision-128k-instruct",
model_kwargs={"stop": ["."]…