microsoft
/

Phi-3-vision-128k-instruct

Text Generation

Model card Files Files and versions Community

Resources

View closed (35)

[Bug] Model Breaking Dynamic Cache

#69 opened 14 days ago by

Extend eos_token_id

#68 opened about 1 month ago by

Is that an error in the backend code?

#67 opened about 1 month ago by

Is it possible to train it on a single 3090 using LoRA on PEFT?

#66 opened about 1 month ago by

Custom Code

#65 opened 2 months ago by

input_ids and attention mask are not of equal size. can someone help me

#64 opened 5 months ago by

Placeholder storage has not been allocated on MPS device!

#63 opened 5 months ago by

Only supporting PIL image?

#62 opened 6 months ago by

Accept multi image ?

#60 opened 6 months ago by

Batch inference

#59 opened 7 months ago by

Fix h_crop and w_crop device

#58 opened 7 months ago by

Not be able to deploy in dedicated inference endpoint for phi3 vision model

#56 opened 7 months ago by

Is JSON mode available in the Phi-3-vision API

#55 opened 7 months ago by

LoRA Finetuning - Text vs Vision Effects

#54 opened 7 months ago by

Will Phi-3 Vision receive the same re-training as Phi-3 Mini ?

#50 opened 8 months ago by

Is there any inference server which can support Phi-3-vision-128K-instruct?

#49 opened 8 months ago by

farzanehnakhaee70

Please add support for ollama.

#48 opened 8 months ago by

Heavy Hallucination | non truncating o/p in Phi 3 Vision Finetuning to convert chart to json

#47 opened 8 months ago by

Vision encoder 1024 output mapping to img_projection 4096 input?

#46 opened 8 months ago by

[AUTOMATED] Model Memory Requirements

#44 opened 8 months ago by

model-sizer-bot

pip install phi3vision

#43 opened 8 months ago by

ninjannnnnnnnnnnnn

phi3 image tokens

#42 opened 8 months ago by

[Issue] Help with the integration of phi-3-vision on llama.cpp

#40 opened 8 months ago by

inference and generation runtime - how to reduce latency

#38 opened 9 months ago by

How to get embedding vectors of images or texts?

#37 opened 9 months ago by

fix-tokenizer

#35 opened 9 months ago by

No support for pipline or TextStreamer

#34 opened 9 months ago by

Over alignment issues

#33 opened 9 months ago by

Handle Batch Sizes (v0.2)

#32 opened 9 months ago by

Shorter context window to reduct inference memory allocation

#31 opened 9 months ago by

Should Phi-3V provide support in llama.cpp?

#24 opened 9 months ago by

Endless blank space generation

#20 opened 9 months ago by

The image provided does not contain a table.

#19 opened 9 months ago by

Finetuning Scripts

#5 opened 9 months ago by