Extend eos_token_id
#68 opened 15 days ago
by
Wovchena
Is that an error in the backend code?
#67 opened 20 days ago
by
MHRDYN7
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1676726678548-6391f365eebba489046d2318.jpeg)
Is it possible to train it on a single 3090 using LoRA on PEFT?
#66 opened 21 days ago
by
boskx
Custom Code
#65 opened about 2 months ago
by
Gliding-Hawk
input_ids and attention mask are not of equal size. can someone help me
#64 opened 4 months ago
by
harsh99
Placeholder storage has not been allocated on MPS device!
#63 opened 5 months ago
by
babulance10
Only supporting PIL image?
#62 opened 5 months ago
by
ryantong3
Accept multi image ?
1
#60 opened 6 months ago
by
AyoubChLin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1674223160074-63c58e4dd5a5cd2043e2f796.jpeg)
Batch inference
2
#59 opened 6 months ago
by
epishchik
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64d9f97295cf13a381fc8898/FHdcUPDiUvfyYF6Xp2_jg.png)
Fix h_crop and w_crop device
#58 opened 6 months ago
by
lutzroeder
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1662132135635-63121c3241ebdfa5f11c051d.jpeg)
Not be able to deploy in dedicated inference endpoint for phi3 vision model
#56 opened 6 months ago
by
Gokulram2710
Is JSON mode available in the Phi-3-vision API
3
#55 opened 7 months ago
by
gaurav646
LoRA Finetuning - Text vs Vision Effects
3
#54 opened 7 months ago
by
brecker
Will Phi-3 Vision receive the same re-training as Phi-3 Mini ?
1
#50 opened 7 months ago
by
Truc95
Is there any inference server which can support Phi-3-vision-128K-instruct?
3
#49 opened 7 months ago
by
farzanehnakhaee70
Please add support for ollama.
#48 opened 7 months ago
by
BrainSlugs83
Heavy Hallucination | non truncating o/p in Phi 3 Vision Finetuning to convert chart to json
1
#47 opened 7 months ago
by
ar9av
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/Lp0HKg1amxxNFa2g5mb1w.png)
Vision encoder 1024 output mapping to img_projection 4096 input?
2
#46 opened 7 months ago
by
hmhanna
[AUTOMATED] Model Memory Requirements
1
#44 opened 8 months ago
by
model-sizer-bot
pip install phi3vision
1
#43 opened 8 months ago
by
ninjannnnnnnnnnnnn
phi3 image tokens
1
#42 opened 8 months ago
by
sachin
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1643284848720-5f339eea7e58354338621575.png)
[Issue] Help with the integration of phi-3-vision on llama.cpp
13
#40 opened 8 months ago
by
ManniX-ITA
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65fb32f58a66679f92b73458/ozQW6W27tVCM-SRouzGJa.jpeg)
inference and generation runtime - how to reduce latency
1
#38 opened 8 months ago
by
wamozart
How to get embedding vectors of images or texts?
1
#37 opened 8 months ago
by
iceleaf97tech
fix-tokenizer
#35 opened 8 months ago
by
xinsu
No support for pipline or TextStreamer
3
#34 opened 8 months ago
by
mohamedlotfy50
Over alignment issues
#33 opened 8 months ago
by
Metricon
![](https://cdn-avatars.huggingface.co/v1/production/uploads/646f1952753be77a8e933f90/OnohCFBLC9aUwqKBTYax8.jpeg)
Handle Batch Sizes (v0.2)
2
#32 opened 8 months ago
by
WilliamSotoM
Shorter context window to reduct inference memory allocation
2
#31 opened 8 months ago
by
JochenGrey
Should Phi-3V provide support in llama.cpp?
6
#24 opened 9 months ago
by
haohoo
Endless blank space generation
1
#20 opened 9 months ago
by
mascIT
The image provided does not contain a table.
#19 opened 9 months ago
by
mascIT
Finetuning Scripts
11
#5 opened 9 months ago
by
abrakaa